Automated lurker advertising system

Abstract

A system configured to control a bid latency process in an advertising bid environment includes a processor and a memory including instructions that, when executed by the processor, cause the processor to receive input including data associated with a product, calculate a product target or a keyword target based on the input, calculate a probability of interruption of the product associated with the product target or the keyword target, based on the received input, calculate a prediction of performance output for at least one bid to be executed for the bid latency process and an estimate of cost per target for the at least one bid, and control the bid latency process to selectively execute a bid for at least one of the product target and the keyword target based on the calculated probability, the prediction of performance output, and the estimate of cost per target.

Description

[0001] Cross-references to related applications

[0002] This application claims priority and benefit to U.S. non-provisional application serial number 18 / 984,310, filed December 17, 2024, and U.S. provisional application number 63 / 560,401, filed March 1, 2024. The entire disclosure of the above-cited applications is incorporated herein by reference. Technical Field

[0003] This disclosure generally relates to pay-per-click advertising systems and methods. Background Technology

[0004] E-commerce systems are well-known in the field and are an effective means of facilitating the exchange of products, goods, and services from one party to another. Typically, e-commerce systems are embodied in marketplaces, where numerous products are offered for sale, and customers can browse or select items to purchase. Such marketplaces can be managed by companies including eBay®, Amazon®, Wayfair®, Costco®, Walmart®, and Target®. With the advent of digital marketplaces, sellers can list products for anyone with an internet connection to purchase. Often, many sellers offer the same or similar products. Shoppers (e.g., users accessing digital marketplaces via the internet) can filter and browse all these products to find what they are looking for.

[0005] One of the issues commonly associated with typical commerce systems and digital marketplaces is the density of potential products that might be available for sale. For example, when a shopper wants to buy a product, they might start by searching on a search engine, which can provide hundreds or thousands of results. Unlike “physical” marketplaces (e.g., physical markets), digital marketplace searches involve at least one specific digital marketplace, or even multiple potential ones, which can provide thousands of results. Any particular product can easily be overwhelmed by the sheer volume of results provided by the search. This can make it difficult for sellers to get their products noticed and sold.

[0006] Furthermore, the seller may have recently created a product or recently placed it on a digital marketplace, but may not know the extent to which they should focus on promoting that product. In this example, the seller may not know what appropriate target Ad CoS (ACoS) to meet or exceed in order to see long-term benefits rather than short-term profits. When product density is high in the marketplace, spending more money to meet and exceed that ACoS enables greater recognition in those digital marketplaces, thereby realizing more potential sales.

[0007] Additionally, sellers can use various metrics to determine the return on investment related to things like advertising expenditure. For example, Return on Advertising Expenditures (ROAS) is one of the most widely used metrics in advertising. ROAS is calculated by dividing advertising sales by advertising expenditure and measures how many dollars of revenue are generated for every dollar spent on advertising. However, such ROAS calculations may ignore the following variable: this variable may limit the power and / or accuracy of ROAS calculations.

[0008] Online advertising (especially in e-commerce) typically uses a first- or second-price auction structure, operating on a cost-per-click basis. The generally accepted process involves bidding on a target (keyword, product, category, etc.) at or above the average competitive bid to win the desired target auction, balancing expected results (e.g., visibility, product traffic, brand sales, or new brand customers) with expected ad spend. Summary of the Invention

[0009] In one implementation, a system configured to control a bid latency process in an advertising bidding environment includes a processor and a memory, the memory including instructions that, when executed by the processor, cause the processor to: receive input including data indicating at least one of the following: a product to be advertised, a product type to be advertised, a market for advertising the product or product type, an expected expenditure amount for advertising the product or product type, a maximum expenditure amount for advertising the product or product type, a type of performance metric associated with advertising the product or product type, a minimum required performance metric associated with advertising the product or product type, and a risk threshold associated with advertising the product or product type; calculate at least one of a product target and a keyword target based on the input; calculate the probability of interruption of a product associated with at least one of the product target and the keyword target; calculate, based on the received input, a prediction of the performance output of at least one bid to be executed for the bid latency process, and an estimate of the cost for each target of the at least one bid; and control the bid latency process to selectively execute bids for at least one of the product target and the keyword target based on the calculated probabilities, the prediction of the performance output, and the cost estimate for each target.

[0010] Among other features, one or more methods include performing steps corresponding to the functions of the system described herein. Among other features, one or more processors or computing devices are configured to perform the functions of the system described herein. Among other features, a non-transitory computer-readable medium stores instructions corresponding to the functions of the system described herein.

[0011] Further applications of this disclosure will become apparent from the detailed description, claims, and drawings. The detailed description and specific examples are intended for illustrative purposes only and are not intended to limit the scope of this disclosure. Attached Figure Description

[0012] This disclosure is best understood in conjunction with the accompanying drawings and the following detailed description. It should be emphasized that, by convention, the various features in the drawings are not drawn to scale. Instead, for clarity, the dimensions of the various features have been arbitrarily enlarged or reduced.

[0013] Figure 1 A schematic block diagram illustrating the principles of the system according to this disclosure is shown in general.

[0014] Figure 2A It illustrates the principles based on this disclosure. Figure 1 A schematic block diagram of a computing device in the form of a smartphone.

[0015] Figure 2B It illustrates the principles based on this disclosure. Figure 1 Desktop computer form of computing devices and Figure 1 A schematic block diagram of a server in the first server form.

[0016] Figure 3 This is a schematic block diagram illustrating a computing device and server operating a digital market according to the principles of this disclosure.

[0017] Figure 4 This is a schematic block diagram illustrating computing devices and servers hosting a digital marketplace based on the principles of this disclosure, the digital marketplace including the attributes of target products and competing products.

[0018] Figure 5 This is a schematic block diagram illustrating a computing device including a graphical user interface according to the principles of this disclosure.

[0019] Figure 6 This is a flowchart illustrating a method for evaluating a product based on the principles of this disclosure.

[0020] Figure 7 This is a flowchart illustrating a method for conducting a competitive assessment of a target product in the market based on the principles of this disclosure.

[0021] Figure 8 This is a schematic block diagram illustrating computing devices and servers operating in a digital market according to the principles of this disclosure.

[0022] Figure 9It is a graphical representation of multiple search terms plotted at points according to the principles of this disclosure, where the points represent the frequency and similarity of search terms associated with the target product relative to competing products.

[0023] Figure 10 It is a graphical representation of multiple search terms drawn at points according to the principles of this disclosure: the points represent the relevance and search volume of search terms associated with the target product relative to competing products.

[0024] Figure 11 This is a flowchart of a method for automating latent activity (e.g., in an advertising bidding environment) based on the principles of this disclosure. Detailed Implementation

[0025] The following discusses various embodiments of this disclosure. While one or more of these embodiments may be preferred, the disclosed embodiments should not be construed as, or otherwise used to limit the scope of this disclosure including the claims. Furthermore, those skilled in the art will understand that the following description has broad application, and the discussion of any embodiment is intended only as an example of that embodiment and is not intended to imply that the scope of this disclosure including the claims is limited to that embodiment.

[0026] In auctions (e.g., ad bidding) of pay-per-click (PPC) advertising systems, an example strategy involves bidding low on a large number of relevant targets (e.g., keywords, products, etc.). This often yields high-return results, but is more volatile. The automated lurking (e.g., ad bidding, such as keyword bidding) systems and methods according to this disclosure are configured to use machine learning components to broadly decompose each component used to optimize the auction strategy in a scalable manner. These systems and methods achieve technical scaling and optimization of the sub-components and perform machine learning to optimize each sub-component. Furthermore, the systems and methods of this disclosure optimize the trade-offs between expected spending, spending volatility, and performance maximization preferences in the e-commerce domain by specifically leveraging opportunities offered by other players in the market. In some contexts, “lurking” as used herein refers to automated lurking during the ad bidding process (this may be referred to as “automated lurking”). In other contexts, “lurking” may refer to a user or consumer viewing or browsing search results, ad links, etc., without clicking on the search results or ad links or visiting the corresponding website (this may be referred to as “browser lurking”).

[0027] Reference Figure 1The schematic block diagram illustrates a system 100 based on the principles of this disclosure. System 100 can be used to provide benefits to one or more users 110, which may include a first user 112, a second user 114, a third user 116, and a fourth user 118, as shown below. Figure 1 As shown. Each user 110 can use one of a variety of computing devices 120, which may include any of a variety of devices that perform computing steps, including but not limited to: a desktop computer 122 used by the first user 112, a laptop computer 124 used by the second user 114, a smartphone 126 used by the third user 116, a camera device 128 used by the fourth user 118, etc. The systems and methods presented herein can be executed on any type of computing device.

[0028] Computing devices 120 may optionally be connected to each other and / or to other resources. Such connections may be wired or wireless and may be achieved using any known wired or wireless communication standards, including but not limited to: Ethernet, 802.11a, 802.11b, 802.11g, and 802.11n, Universal Serial Bus (USB), Bluetooth, cellular, Near Field Communication (NFC), Bluetooth Smart, ZigBee, etc. Figure 1 In the illustration, wired communication is shown with solid lines, while wireless communication is shown with dashed lines.

[0029] Routing can be achieved by using router 130 and / or by other means. Figure 1 Communication between various components. Router 130 can be of any type known in the art and can be designed for wired and / or wireless communication via any known communication standard, including but not limited to those listed herein. Router 130 may include, for example: a first router 132 that facilitates communication to and / or from desktop computer 122; a second router 134 that facilitates communication to and / or from laptop computer 124; a third router 136 that facilitates communication to and / or from smartphone 126; and a fourth router 138 that facilitates communication to and / or from camera device 128.

[0030] Router 130 can facilitate communication between computing device 120 and one or more networks 140, which can include any type of network, including but not limited to local area networks such as local area network 142 and wide area networks such as wide area network 144. In some embodiments, local area network 142 can be a network serving entities such as enterprises, non-profit entities, government organizations, etc. Wide area network 144 can provide communication for multiple entities and / or individuals, and in some embodiments, it can be the Internet. Local area network 142 can communicate with wide area network 144. If needed, one or more routers or other devices can be used to facilitate such communication.

[0031] Network 140 can store information on server 150 or other information storage devices. As shown, first server 152 can be connected to local area network 142, and therefore can communicate with devices connected to local area network 142 (such as desktop computer 122 and laptop computer 124). Second server 154 can be connected to wide area network 144, and therefore can communicate with devices connected to wide area network 144 (such as smartphone 126 and camera device 128). If needed, second server 154 can be a web server, providing web pages, network connectivity services, executable code designed to run on the Internet, and / or other functions that facilitate the provision of information and / or services on wide area network 144.

[0032] Reference Figure 2A The schematic block diagram illustrates an exemplary computing device among a plurality of computing devices 120, which enables the implementation of the present disclosure in a standalone computing environment. The computing device may be, for example... Figure 1 The smartphone 126. However, this specification envisions that the computing device 120 may include... Figure 1 Any one or any other type of computing device among those computing devices 120 described herein.

[0033] As shown, smartphone 126 may include processor 210, which is designed to execute instructions on data. Processor 210 may be any of a variety of types, including microprocessors with x86-based architectures or other architectures known in the art, application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), etc. Processor 210 may optionally include multiple processing elements or "cores". Processor 210 may include a cache that provides temporary storage for data generated incidentally during operations on processor 210.

[0034] The smartphone 126 may also include a memory 220, which may be volatile memory, such as random access memory (RAM). The memory 220 may include one or more memory modules. The memory 220 may include executable instructions, data referenced by such executable instructions, and / or any other data that may be advantageously made readily accessible to the processor 210.

[0035] The smartphone 126 may also include a data storage 230, which may be a non-volatile memory such as a hard disk drive or flash memory. The data storage 230 may include one or more data storage elements. The data storage 230 may store executable code, such as an operating system and / or various programs to run on the smartphone 126. The data storage 230 may also store data to be used by such programs. For the systems and methods of this disclosure, the data storage 230 may store computer-executable code associated with the evaluation module 232, text analysis module 238, filtering module 235, comparison module 234, recommendation module 236, and competitiveness score generation module 233. The data storage 230 may also include data associated with: descriptive terms 241 related to the target product and / or competing products, relevant descriptive terms 242 associated with either the target product or competing products, competitiveness scores 239, and actionable reports 237. This data stored by the data storage 230 may be retained on the data storage 230 for any duration, and some data may be created or overwritten at any time to facilitate the methods described herein.

[0036] Smartphone 126 may also include one or more wired transmitters / receivers 240, which can facilitate communication between smartphone 126 and any other device (e.g., Figure 1 Wired communication between the transmitter / receiver 240 and other computing devices 120, servers 150, and / or routers 130. The wired transmitter / receiver 240 can communicate via any known wired protocol, including but not limited to... Figure 1 Any wired protocol described herein. In some implementations, the wired transmitter / receiver 240 may include an Ethernet adapter, a Universal Serial Bus (USB) adapter, etc.

[0037] Smartphone 126 may also include one or more wireless transmitters / receivers 250, which can facilitate communication between smartphone 126 and any other device (e.g., Figure 1 Wireless communication between the wireless transmitter / receiver 250 and other computing devices 120, servers 150, and / or routers 130. The wireless transmitter / receiver 250 can communicate via any known wireless protocol, including but not limited to... Figure 1 Any wireless protocol described herein. In some implementations, the wireless transmitter / receiver 250 may include a Wi-Fi adapter, Bluetooth adapter, cellular adapter, etc. Either the wired transmitter / receiver 240 or the wireless transmitter / receiver 250 may be associated with the network interface device (NID) 280. The network interface device 280 may provide connectivity to any network (e.g., a wide area network (WAN), local area network (LAN), wireless local area network (WLAN), wireless personal area network (WPAN), wireless wide area network (WWAN), or other networks) via the Internet.

[0038] Smart phone 126 may also include one or more user inputs 260, which receive data from sources such as... Figure 1 User input 260 may be the input of any user 110. User 110 described herein may be referred to as the seller of the target product. User input 260 may be integrated into smartphone 126, or may be separate from smartphone 126 and connected to smartphone 126 via a wired or wireless connection that may operate via wired transmitter / receiver 240 and / or wireless transmitter / receiver 250. User input 260 may include elements such as touch screen, buttons, keyboard, mouse, trackball, trackpad, stylus, digitizer, digital camera, microphone and / or other user input devices known in the art.

[0039] Smart phone 126 may also include one or more user outputs 270, which output to, for example, Figure 1 The user output 270 provides output to any user of user 110. The user output 270 may be integrated into the smartphone 126, or it may be separate from the smartphone 126 and connected to the smartphone 126 via a wired or wireless connection, which may operate via a wired transmitter / receiver 240 and / or a wireless transmitter / receiver 250. The user output 270 may include elements such as a display screen, speaker, vibration device, LED or other light, and / or other output devices known in the art. In some embodiments, one or more of the user inputs 260 may be combined with one or more of the user outputs 270; this may be the case with a touchscreen. In some embodiments, the user output 270 may present a graphical user interface to a user through which the user interacts with the smartphone 126 to influence the methods and processes described herein.

[0040] The smartphone 126 may include various other components not shown or described herein. With the aid of this disclosure, those skilled in the art will recognize that, in addition to combining… Figure 2AAny such component, other than those shown and described or as an alternative, may be used to perform the contents of this disclosure.

[0041] The smartphone 126 can execute the contents of this disclosure in an independent computing environment, i.e., without relying on communication with other devices such as other computing devices 120 or server 150. This specification also envisions that any one of the evaluation module 232, competitiveness score generation module 233, comparison module 234, filtering module 235, recommendation module 236, and text analysis module 238 can be distributed across multiple computing devices (e.g., ...). Figure 1 The computing device 120) and / or any server (e.g., Figure 1 In 150). In other embodiments, this disclosure can be used in different computing environments. (Will be combined with...) Figure 2B An example of a client / server environment is shown and described.

[0042] Reference Figure 2B The schematic block diagram shows Figure 1 Desktop computer 122 form computing device and Figure 1 The first server 152 is a type of server that can collaborate to implement the client / server architecture of this disclosure. As shown, desktop computer 122 can be a "dumb terminal" that works in conjunction with the first server 152.

[0043] Therefore, desktop computer 122 may only have the ability to communicate with users (e.g., Figure 1 The desktop computer 122 may include the hardware required for interfacing with the first user 112 and communicating with the first server 152. Therefore, the desktop computer 122 may include one or more user inputs 260, one or more user outputs 270, one or more wired transmitters / receivers 240, and / or one or more wireless transmitters / receivers 250. Similarly, any of the wired transmitters / receivers 240 or wireless transmitters / receivers 250 may be associated with the NID 280a. The NID 280a may provide connectivity to any network via the Internet, such as a wide area network (WAN), local area network (LAN), wireless local area network (WLAN), wireless personal area network (WPAN), wireless wide area network (WWAN), or other networks (of which the first server 152 forms part). These components may be combined... Figure 2A As described.

[0044] Computational functions (aside from those incidentally generated from receiving input from the user and transmitting output to the user) can be performed wholly or partially at the first server 152. Therefore, the processor 210, memory 220, data storage 230, wired transmitter / receiver 240, and wireless transmitter / receiver 250 can be housed in the first server 152. These components can also be combined. Figure 1 A describes it.

[0045] In operation, desktop computer 122 can receive input from a user via user input 260. The user input can be transmitted to first server 152 via wired transmitter / receiver 240 and / or wireless transmitter / receiver 250. The user input can also be transmitted by any intermediate device, such as first router 132 and any other device in local area network 142 that needs to transmit user input from first router 132 to first server 152.

[0046] The first server 152 can perform any necessary processing steps in response to the receipt of user input. The first server 152 can then send user output to the user via wired transmitter / receiver 240 and / or wireless transmitter / receiver 250. This user output can also be transmitted by any intermediate device, such as the first router 132 and any other device in the local area network 142 (or, alternatively, the wide area network 144) that needs to transmit the user output from the first server 152 to the first router 132. The user output can then be provided to the user via user output 270. In some embodiments, user output 270 can present a graphical user interface to the user, which, according to the method described herein, displays a list of relevant descriptive terms 242 for the target product and competing products, and displays an actionable report describing the expected performance of the target product in the computer networking market relative to at least one organic competing product also presented in the computer networking market.

[0047] Reference Figure 3 The schematic block diagram illustrates a computing device 322 (similar to) operating a digital market according to the principles of this disclosure. Figure 1 Any of the computing devices shown) and server 350 (similar to Figure 1Any of the servers shown can collaborate to implement the client / server architecture of this disclosure. As shown, computing device 322 can be operatively coupled to server 350 via NID 380, as described herein. This operative coupling allows computing device 322 to access digital marketplace 382, ​​which sells target and competing products, when appropriate. Digital marketplace 382 can be any network-accessible website listing multiple products, which, when visited by a user, allows the user to review products, rate products, purchase products, and perform other tasks related to digital commerce. Digital marketplace 382 can be managed by companies including eBay®, Amazon®, Wayfair®, Costco®, Walmart®, and Target®. When purchasing products, consumers can have the purchased products delivered to their home or business for use. In some implementations, digital marketplace 382 can be any of multiple websites for which server 350 provides storage and processing resources.

[0048] As described herein, computing device 322 may include processor 310, memory 320, user input 360, user output 370, and data storage 330, which are combined with Figure 2A and Figure 2B The similar components described operate similarly. Data storage 330 may include the modules described herein, including evaluation module 332, competitiveness score generation module 333, comparison module 334, filtering module 335, recommendation module 336, and text analysis module 338.

[0049] During operation, evaluation module 332 can evaluate certain attributes of the target product. The target product described herein is a specific target product that a user (e.g., a seller) of computing device 322 is seeking to discover its competitiveness in a particular market. For example, the target product could be a product that the user is currently selling or wants to sell on a digital marketplace 382 hosted on server 350. To determine the competitiveness of the target product, evaluation module 332 can access certain data about the target product presented on server 350. Evaluation module 332 can access the data by sending a data request via NID 380 through either a wired (e.g., via wired transmitter / receiver 340) or wireless (e.g., via wireless transmitter / receiver 350) connection.

[0050] Data requests can be requests for attributes of the target product. While any number of attributes about the target product can be requested, evaluation module 332 can request specific attributes that will be used to develop an actionable report 337 regarding the target's competitiveness in digital marketplace 382. A first attribute can describe a rating provided by at least one buyer of the target product on digital marketplace 382. Typically, digital marketplace 382 provides consumers with a graphical user interface (GUI) that allows these consumers to rate products they purchase on digital marketplace 382. In a particular implementation, consumers / buyers of the target product can use a five-star rating system to rate the target product. A one-star rating would indicate that the consumer / buyer rated the target product poorly, while a five-star rating would indicate that the consumer / buyer rated the target product very well. Therefore, evaluation module 332 can use each star or the average of these stars as input to create actionable report 337.

[0051] The second attribute may include reviews and / or user-generated content associated with the target product. Similarly, the digital marketplace 382 typically provides a GUI that allows consumers of the target product to input text describing their experience with the product. This text may include specific positive or negative keywords describing the consumer's experience with the target product. Using this data, the evaluation module 332 can enable the text analysis module 338, in some implementations, to parse each review against these keywords describing the target product. Furthermore, the text analysis module 338 can also extract keywords describing certain features of the target product. As an example, the phrase "ergonomic handle" can be extracted by the text analysis module 338, which not only describes the target product as including a handle but also describes the handle as an "ergonomic" handle, thus giving the perception that the consumer who gave this review liked the fit or feel of the target product.

[0052] The third attribute can be similar to the second attribute, as evaluation module 332 determines the number of reviews associated with the target product presented on digital marketplace 382. The number of reviews can indicate the level of engagement with the target product, whether it is derogatory or positive. Along with the text content of these reviews, the number of reviews associated with the target product can be used to help create actionable reports based on engagement with the target product within digital marketplace 382.

[0053] The fourth attribute can include the listed price of the target product. Although the amount charged for purchasing the product may not indicate the value of the target product, it can indicate its market value or current price point (whether incorrect or correct) relative to other similar competing products.

[0054] The fifth attribute may also include the target product's ranking relative to at least one natural competitor. This ranking may be the result of the target product's average or cumulative rating relative to natural competitors. Typically, digital marketplaces 382 allow buyers to list natural competitors and the target product by average rating. By doing so, the evaluation module 332 can understand the target product's ranking relative to at least one natural competitor and use this information to develop an actionable report 337.

[0055] Evaluation module 332 can also determine at least one similar attribute of a naturally competing product, which is similar to those attributes that evaluation module 332 has found for the target product. In the context of this specification, the term "naturally competing product" should be understood as any product ranked on the digital marketplace 382 based on consumer reviews. Therefore, a "natural" competing product is one that is naturally ranked based on reviews provided by past consumers, unlike products that are given "top shelf" priority after payment to obtain this position. This natural ranking nature of products on the digital marketplace 382 is often intended to provide potential consumers with evidence that others appreciate the product. A "competing" product is any product similar to the target product but sold by a seller other than the seller of the target product. The "similarity" of the target product relative to at least one naturally competing product depends on the data obtained by text analysis module 338, and particularly on the analysis of the descriptive terms 341 associated with each of these types of products. In a particular embodiment, text analysis module 338 can also obtain descriptive data associated with each target product and naturally competing product based on their detail pages. Similarly, the digital marketplace 382 allows for the posting of product descriptions alongside each product, outlining its features, physical characteristics, and claimed advantages as a premium product. All of this is presented as textual information to potential consumers on the GUI to entice them to purchase the product. The text analysis module 338 can analyze this text and use a parsing process to extract keywords for comparing text associated with the target product with text associated with naturally competing products.

[0056] Once the computing device 322 has obtained attributes associated with the target product and at least one natural competitor product via the evaluation module 332, descriptive terms 341 describing these attributes can be listed for use by the filtering module 335 in some embodiments. The filtering module 335 can be used to filter the descriptive terms 341 to retain only those relevant to the purchase of the target product in the digital marketplace 382. For example, some descriptive terms 341 may correctly or incorrectly include the color or color scheme of the target product or a natural competitor product. While some consumers may appreciate a particular color of a product, these may not be decisive factors in attracting consumers to purchase the target product or a natural competitor product. This is especially true when the purchase history associated with the target product or a natural competitor product indicates that any particular color has not been overwhelmingly purchased over another color. In this particular example, although the color of the product is a descriptive term 341 parsed from the product by the text analysis module 338, it may not necessarily be a relevant descriptive term 341, and such information can be filtered out by the filtering module 335 to obtain only those relevant descriptive terms 342 associated with either the target product or any of the naturally competing products.

[0057] In some examples, it's possible to target competing products without providing any keywords. For instance, you can target a competing product using keywords ("keyword targeting"), or you can target the product itself ("product targeting," such as causing Market 382 to place an ad next to that product). Therefore, in some examples, for a given product, you can target keywords to a specific competing product, while in other examples, you can target the competing product itself, rather than its keywords.

[0058] In a more general example, the filtering module 335 can narrow down the descriptive terms 341 of interest by analyzing metrics collected on sufficiently "mature" keywords (e.g., sales > 2), while budding keywords may lack sufficient data to influence predictions regarding the purchase of the target product or naturally competing products. Click-through rates and conversion rates (clicks leading to a purchase) associated with any given product can be considered based on the keywords used to search for the product. In these examples, a lack of data on a particular descriptive term 341 can also filter out that particular descriptive term 341 to obtain the relevant descriptive terms 342 as described herein. It should also be understood that the filtering module 335 can filter descriptive terms 341 to obtain relevant descriptive terms 342 for any other reason, and these other reasons are contemplated in this specification.

[0059] Once the relevant descriptive terms 342 are determined, these terms can be sent to the comparison module 334 to compare the relevant descriptive terms 342 of the target product with those associated with at least one natural competitor product. Although this specification describes the comparison process as being conducted between a single natural competitor product (e.g., "at least one") and the target product, any number of natural competitors products can be compared with the target product. In a particular example, the comparison module 334 may compare the top 10 natural competitors products with the target product.

[0060] During the execution of comparison module 334 by processor 310, descriptive terms 341 may be compared to generate a competitiveness score 339 using competitiveness score generation module 333 executed by processor 310. In some embodiments, the competitiveness score may use any process or algorithm for defining how a target product can or cannot compete with any discovered naturally competing products.

[0061] During operation, the recommendation module 336 may receive the competitiveness score 339 and other data from the digital marketplace 382 hosted by server 350. This other data may include revenue data (if any) associated with organic competitors and the target product. For example, if a click-through rate for any given product (e.g., the target product or an organic competitor) leads to a purchase, this conversion rate data, along with the product's pricing data, may be passed to the recommendation module 336. The recommendation module 336 can then provide a recommendation describing the target product's ability (or inability) to compete with at least one organic competitor. In some implementations, a threshold competitiveness score may be set such that the report provided by the recommendation module 336 instructs the seller of the target product whether to continue selling the product on the digital marketplace 382. Alternatively, if the competitiveness score does not meet the threshold, the competitiveness score generation module 333 may not forward the competitiveness score to the recommendation module 336 to generate an actionable report 337. Alternatively or additionally, if the competitiveness score does not meet the threshold, the competitiveness score generation module 333 may pass a threshold failure signal to the recommendation module 336, indicating a non-competitive status for the target product. When the threshold competitiveness score is not reached, the recommendation module 336 can provide the seller with an instruction not to recommend that the seller initiate or continue to sell the target product on the digital marketplace 382.

[0062] Upon reaching a threshold competitiveness score, the recommendation module 336 can provide additional economic data describing the price point and ACoS statistics to increase revenue. Similarly, the seller of the target product may not know what appropriate target advertising cost of sales (ACoS) and at what price point to sell the target product in order to see long-term revenue rather than short-term profit. The recommendation module 336 provides this information based on the competitiveness score 339 generated by the competitiveness score generation module 333 and the revenue data received from the digital marketplace 382. In a specific example, the revenue potential of the target product can be determined by the recommendation module 336 through calculating the advertising spend profit margin, advertising spend potential, and revenue potential. The advertising spend profit margin can be calculated by multiplying the target ACoS by the price of the target product. The target ACoS can be determined and set by the seller based on available capital, or it can be set by the seller based on the percentage of revenue received from sales of the target product on the digital marketplace 382 to date and manufacturing costs. The advertising spend potential can then be calculated by multiplying the monthly opportunity unit (OU) by the spending profit margin. The monthly OU can be calculated based on the target product's click-through conversion rate, which is the result of a sale of the target product after a buyer views the product. Revenue potential can then be calculated by multiplying OU by the price of the target product. The revenue potential of each of the target product and naturally competing products can be ranked to determine the target product's placement in digital marketplace 382.

[0063] In some implementations, the recommendations presented by recommendation module 336 (e.g., actionable report 337) can be refined by inputting an estimated bid amount from digital marketplace 382 to “win” ad placement for the target product. In addition to selling products, digital marketplace 382 can also participate in presenting ads to potential buyers of one or more products. These ads may appear as banners or other sub-sections of the GUI presented to buyers, or as pop-up ads. These forms of advertising present alternative products that potential buyers are seeking to purchase in real time. These ads can present the target product and persuade buyers to buy the target product instead of competitors' products. Therefore, investment may be required to increase purchase instances of the target product. The system and method can also present the target product’s sellers on actionable report 337: how much additional investment might be needed to win ad placement based on keywords associated with the target product and entered into searches by potential users. For example, the required investment can be calculated by multiplying the estimated bid amount by the product of the target product’s click-through rate and the impressions (e.g., usage counts) of a specific keyword associated with the target product and organic competing products used in searches for those products. The return on investment (ROI) can then be calculated by subtracting the required investment from the return on investment and multiplying it by the advertising expenditure potential. Products with no potential (or low potential) receive suggested outputs through the recommendation module 336 and its actionable report 337 regarding why they are not competitive or have poor conversion rates, allowing these attributes of the target product to be improved for future potential, or the money spent on selling the target product to be reallocated for other purposes.

[0064] Figure 4 This is a schematic block diagram illustrating a computing device 420 and a server 452 hosting a digital marketplace 482 (including attributes of the target product and competing products), which can collaborate to implement the contents of this disclosure using a client / server architecture. As described herein, an evaluation module 432 can evaluate certain attributes of the target product. The target product described herein is a specific target that a user (e.g., a seller) of the computing device 420 is seeking to discover the competitiveness of that product in a particular market. For example, the target product could be a product that the user is currently selling or wants to sell on the digital marketplace 482 hosted by the server 452. To know the competitiveness of the target product, the evaluation module 432 can access certain data about the target product presented on the server 452. The evaluation module 432 can access the data by sending a data request via NID 480 through either a wired (e.g., via a wired transmitter / receiver 440) or wireless (e.g., via a wireless transmitter / receiver 450) connection.

[0065] Data requests can be requests for attributes of the target product. While any number of attributes about the target product can be requested, evaluation module 432 can request specific attributes that will be used to develop an actionable report on the target's competitiveness in digital marketplace 482. A first attribute can describe a rating 483 provided by at least one purchaser of the target product on digital marketplace 482. Typically, digital marketplace 482 provides consumers with a graphical user interface (GUI) that allows these consumers to rate products they purchase on digital marketplace 482. In a particular implementation, consumers / purchasers of the target product can use a five-star rating system to rate the target product. A one-star rating would indicate that the consumer / purchaser rated the target product poorly, while a five-star rating would indicate that the consumer / purchaser rated the target product very well. Therefore, evaluation module 432 can use each star or the average of these stars as input to create an actionable report.

[0066] The second attribute may include content 486 of reviews and descriptions associated with the target product. Similarly, the digital marketplace 482 typically provides a GUI that allows consumers of the target product to input text describing their experience with the product. This text may include specific positive or negative keywords describing the consumer's experience with the target product. Using this data, the evaluation module 432 may enable the text analysis module 438 to parse each review describing the target product in some implementations. Furthermore, the text analysis module 438 may also extract keywords describing certain features of the target product. As an example, the phrase "ergonomic handle" can be extracted by the text analysis module 438, which not only describes the target product as including a handle but also describes the handle as an "ergonomic" handle, thus giving the perception that the consumer who gave this review liked the fit of the target product.

[0067] The third attribute could be the number of reviews (484) related to the target product presented on the digital marketplace (482). The number of reviews (484) can indicate the level of engagement with the target product, whether it's negative or positive. Along with the text content of these reviews, the number of reviews associated with the target product can be used to help create actionable reports based on engagement with the target product within the digital marketplace (482).

[0068] The fourth attribute could include the target product's listed price of 485. While the amount charged for purchasing the product may not indicate the value of the target product, it can indicate its market value or current price point (whether accurate or inaccurate) relative to other similar competing products.

[0069] The fifth attribute may also include the target product's ranking relative to at least one natural competitor product 487. This ranking may be the result of the target product's average or cumulative rating relative to natural competitors. Typically, the digital marketplace 482 allows buyers to list natural competitors and the target product according to average ratings. By doing so, the evaluation module 432 can understand the target product's ranking relative to at least one natural competitor product and use this information to develop actionable reports.

[0070] Each of these target product attributes can be requested by computing device 420 and its evaluation module 432, and transmitted by server 452 upon request. Furthermore, similar attributes associated with at least one natural competing product can also be requested and sent to computing device 420. These natural product attributes may include competitor product ratings 488, number of competitor product reviews 489, competitor product price 490, competitor product content 491, and competitor product ranking 492. Each of these competitor product attributes may be similar to those attributes associated with and described herein in conjunction with the target product.

[0071] Figure 5 This is a schematic block diagram illustrating a computing device 520, which includes a graphical user interface 522 for enabling the implementation of the present disclosure within a client / server architecture. The graphical user interface 522 can be used by a seller of a target product to evaluate the competitiveness of the target product, as described herein. As described herein, the computing device 520 includes a filtering module 535. The filtering module 535 can be used to filter descriptive terms 541 to retain only those relevant descriptive terms 542 that would lead to the purchase of the target product in a digital marketplace.

[0072] Filtering module 535 may include various types of filters to filter descriptive terms 541 into relevant descriptive terms 542. These filters may include an impression filter 524, a click-through rate filter 526, and a conversion rate filter 528, each of which may result in the removal of the following descriptive term 541: that descriptive term 541 does not lead to the purchase of the target product or any organically compared product. As described herein, the impression filter 524 may be provided with the following counts: the number of times an advertisement (whether a banner, button, or text link) associated with the target product or competing products has been (or will be) exposed to a potential buyer and has already led to the purchase of that product. Therefore, the impression filter 524 may filter out those cases where a potential buyer did not see or have the advertisement displayed but still resulted in a purchase. The click-through rate filter 526 may filter out the following descriptive terms: despite the wording of the advertisement, the descriptive term did not lead to the selection of the advertisement or the purchase of the product. The conversion rate filter 528 may filter out the following descriptive terms: despite the wording of the advertisement and the potential buyer selecting the advertisement, the descriptive term did not lead to the purchase of the product.

[0073] By filtering descriptive terms via filter module 535 and its associated filters 524, 526, and 528, GUI 522 can display to the seller of the target product relevant descriptive terms 542 used for analyzing the competitiveness of the target product. Although Figure 5 The use of specific filters 524, 526, and 528 to filter descriptive term 541 is shown, but this specification envisions that any standard can be used to filter descriptive term 541.

[0074] In some implementations, system 100 and / or any computing device or other device or system described herein may perform the methods described herein. However, the methods described herein are not intended to be limiting, and any type of software executing on a controller or processor may perform the methods described herein without departing from the scope of this disclosure.

[0075] Figure 6 This is a flowchart illustrating a method 600 for evaluating a product according to the principles of this disclosure. Method 600 may begin at block 605, using an evaluation module executed by a processor to evaluate attributes of a target product. As described herein, the evaluation of a target product (or any other competing product) may indicate certain attributes of the target product. Although any number of attributes regarding the target product may be requested, the evaluation module may request specific attributes that will be used to develop an actionable report on the target's competitiveness in the digital market.

[0076] At block 610, method 600 may further include listing relevant descriptive terms for the target product, which describe the attributes of the target product. The listing of relevant descriptive terms may also be performed by an evaluation module executed by the processor of a computing device. In some embodiments, the list of relevant descriptive terms may be generated based on filtering all descriptive terms generated for the target product as described herein. Some irrelevant information may exist, which can be filtered out from the descriptive terms generated based on the attributes of the target product; this irrelevant information does not need to appear in the operational report.

[0077] Method 600 may continue at block 615, accessing the computer networking marketplace via NID and identifying at least one natural competitor product that matches at least one descriptive term. This identification may implement an evaluation module to compare the descriptive term associated with the target product with any generated descriptive terms associated with any natural competitor product. In some embodiments, this matching process of the descriptive terms associated with the target product and the descriptive terms associated with the natural competitor product may be performed before or after the filtering module described herein filters the descriptive terms. When performed before filtering, more natural competitor products may be matched, while when performed after filtering, relatively fewer natural competitor products may be matched due to the smaller list of relevant descriptive terms.

[0078] Method 600 may further include, at block 620, comparing descriptive terms of the target product with descriptive terms associated with at least one natural competing product to generate a competitiveness score. This may be accomplished via execution of a comparison module 620 executed by the processor. During the execution of the comparison module by the processor, descriptive terms may be compared to generate a competitiveness score using a competitiveness score generation module executed by the processor. In some embodiments, the competitiveness score may use any process or algorithm for defining how the target product can or cannot compete with any discovered natural competing products.

[0079] At block 625, method 600 may further include generating an actionable report describing the expected performance of the target product relative to at least one natural competitor in a computer networking marketplace. The actionable report may be generated via a recommendation module executed by a processor. During operation, the recommendation module may receive the competitiveness score and other data from the server-hosted digital marketplace. This other data may include revenue data (if any) associated with the natural competitors and the target product. For example, if a click-through rate for any given product (e.g., the target product or a natural competitor) leads to a purchase, this conversion rate data, along with the product's pricing data, may be passed to the recommendation module. The recommendation module can then provide a recommendation describing the target product's ability (or inability) to compete with at least one natural competitor. In some implementations, a threshold competitiveness score may be set such that the report provided by recommendation module 336 instructs the seller of the target product whether to continue selling the product in the digital marketplace. Alternatively, if the competitiveness score does not meet the threshold, the competitiveness score generation module may not forward the competitiveness score to the recommendation module to generate the actionable report. When the threshold competitiveness score is not met, the recommendation module simply provides the seller with an instruction not to recommend that the seller initiate or continue selling the target product in the digital marketplace.

[0080] Upon reaching a threshold competitiveness score, the recommendation module can provide additional economic data describing the price point and ACoS statistics to increase revenue. Similarly, the seller of a target product may not know what appropriate target ACoS to achieve to see long-term revenue rather than short-term profit, or at what price point to sell the target product. The recommendation module provides this information based on the competitiveness score generated by the competitiveness score generation module and revenue data received from the digital marketplace. In a specific example, the revenue potential of a target product can be determined by calculating the ad spend profit margin, ad spend potential, and revenue potential through the recommendation module. The ad spend profit margin can be calculated by multiplying the target ACoS by the price of the target product. The target ACoS can be determined and set by the seller based on available capital, or it can be set by the seller based on the percentage of revenue received from sales of the target product from the digital marketplace to date and manufacturing costs. The ad spend potential can then be calculated by multiplying the monthly opportunity unit (OU) by the ad spend profit margin. The monthly OU can be calculated based on the target product's click-through rate, which is the result of a sale of the target product after a buyer views the product. The revenue potential can then be calculated by multiplying the OU by the price of the target product. It is possible to rank the revenue potential of each of the target product and naturally competing products to determine the placement of the target product in the digital market.

[0081] At this point, method 600 can end.

[0082] Figure 7 This is a flowchart illustrating a method 700 for providing a competitiveness assessment of a target product in the market according to the principles of this disclosure. Here, method 700 may begin at block 705, assessing the target product to determine its attributes. In some embodiments, the assessment may be performed via the execution of an assessment module. In some embodiments, the assessment may be performed by requesting descriptive terms about the target product at a GUI. Alternatively or alternatively, the assessment module may access a digital marketplace to retrieve descriptive terms via the text analysis module described herein for assessment. Alternatively or alternatively, certain input devices, such as digital camera devices, may be used to image the target product and infer certain characteristics of the product, such as size, color, texture, etc.

[0083] Method 700 can continue at block 710, whereby, during processor execution, a digital marketplace is accessed to identify at least one natural competitor to the target product. In this implementation, the evaluation module may access certain data about the target product, such as descriptive terms, and cross-reference those descriptive terms to determine whether at least one descriptive term matches any competing product listed in the digital marketplace.

[0084] At block 715, method 700 may include calculating a competitiveness score relating to the ability of a target product to compete with at least one natural competitor. This process may be performed when a processor of a computing device accessing a digital marketplace executes a competitiveness score generator. In some implementations, the competitiveness score may use any process or algorithm to define how the target product can or cannot compete with any discovered natural competitors.

[0085] Method 700 may further include, at block 720, generating an actionable report based on the target product's ability to compete with at least one naturally competing product. During operation, a recommendation module executed by the processor may receive a competitiveness score and other data from a server-hosted digital marketplace. This other data may include revenue data (if any) associated with the naturally competing and target products. For example, if a click-through rate for any given product (e.g., the target product or a naturally competing product) leads to a purchase, this conversion rate data, along with the product's pricing data, may be passed to the recommendation module. The recommendation module can then provide a recommendation describing the target product's ability (or inability) to compete with at least one naturally competing product. In some implementations, a threshold competitiveness score may be set such that the report provided by the recommendation module instructs the seller of the target product whether to continue selling the product on the digital marketplace. Alternatively, if the competitiveness score does not meet the threshold, the competitiveness score generation module may not forward the competitiveness score to the recommendation module to generate an actionable report. When the threshold competitiveness score is not met, the recommendation module simply provides the seller with an instruction not to recommend that the seller initiate or continue selling the target product on the digital marketplace. At this point, method 700 may terminate.

[0086] Figure 8 This is a schematic block diagram showing a computing device 822 and a server 852 running a digital marketplace 882, which can collaborate to implement the present disclosure using a client / server architecture. In addition to combining... Figures 1 to 7 The described report provides an actionable overview of the target's competitiveness in the digital market 882. Figure 3 In addition to (337), the computing device 822 may also: describe an actionability report 837, which describes sustainable and feasible growth over time on an e-commerce platform (e.g., digital marketplace 882) at the product level; and provide a winability report 804, which describes the probability of winning each search term (e.g., associating a target product with a search term) at any given point in time and the estimated cost of winning those search terms. In some implementations, the actionability report 837 and the winability report 804 may provide users with instructions on how to optimize advertising and search engine implementations to increase revenue.

[0087] As described herein, computing device 822 may include processor 810, memory 820, user input 860, user output 870, and data storage 830, which are combined with, for example, Figure 2A and Figure 2B The similar components described herein operate similarly. Data storage 830 may include the modules described herein, including comparison module 834 and revenue module 899.

[0088] The described computing device 822 may include any module, data storage 830, or data stored on a computer, as described herein. Figure 3 Those described herein. In the implementations described herein, similar combinations can be used. Figure 3 The comparison module 334 described is used to provide an operational report 837. Although these modules (e.g., comparison module 834) can be similar to... Figure 3 Those described in the text, but Figure 8 The modules within can perform the additional and different processes described herein to provide actionable reports 837 indicating how advertising and search engine implementations should be optimized.

[0089] In some implementations, computing device 822 can initially identify any competing products that compete with the target product at any given time. Computing device 822 can achieve this by accessing a search engine 894 associated with digital marketplace 882 via processor 810 and NID 880 of computing device 822. When accessing search engine 894, processor 810 can retrieve data describing the frequency of occurrence of one or more search terms associated with the target product. Additionally, processor 810 can obtain data related to the ranking of those search terms. This data can describe the overlap between the target product and any competing products associated with the same search terms. Furthermore, this data can describe the similarity in ranking of search terms associated with the target product and each competing product. For example, in the case of the target product being athletic shoes, some relevant search terms could include running, hiking, basketball, tennis, sole, shoelaces, and marathon, as well as other potential terms associated with the target product, athletic shoes. This data may also include which competing products also have similar rankings for these terms. For example, a competing product that matches the target product 9 out of 10 search terms will "rank higher" compared to a competing product that matches 4 out of 10 search terms.

[0090] In a particular embodiment, processor 810 may access the data, for example, using a search query website such as Google® Trends®. Processor 810 may use these types of websites to access multiple search queries targeting specific terms associated with any target product and any number of competing products. Processor 810 may access search query websites to automatically access search query queries, thereby obtaining the data used herein by computing device 822. While specific search query websites are contemplated herein, this specification also contemplates that processor 810 may access other search query databases, whether or not those databases are accessible to a user via a website.

[0091] The computing device 822 also includes a machine learning module 896 (e.g., which may be referred to herein as machine learning model 896). The machine learning module 896 can construct multiple mathematical models that provide a competition set report 898 describing a set of competing products that compete with the target product. As with each machine learning module 896, it can be "taught" using multiple sets of target product search terms and rankings, as well as multiple sets of competing product search terms and rankings, as input. Similarly, the processor 810 can access multiple sets of target product search terms and rankings, as well as multiple sets of competing product search terms and rankings, via a specific search query website or database.

[0092] In some embodiments, the machine learning module 896 may determine such relevance when executed by the processor 810. In other embodiments, the machine learning module 896 may determine such relevance based on any machine learning or neural network methods known in the art or developed in the future. In certain embodiments, the machine learning module 896 may implement unsupervised learning clustering techniques. For example, in some embodiments, the machine learning module may use a hierarchical neural network topology to model the relationships between multiple sets of target product search terms and rankings, and multiple sets of competing product search terms and rankings. In some embodiments, such a neural network may include: an input layer (e.g., multiple sets of target product search terms and rankings, and multiple sets of competing product search terms and rankings), which includes a set of known recorded values ​​of these parameters, settings, indicators, and using each of the data metrics; and an output layer that includes a predicted optimal competitive set report 898 based on the set of values ​​of the known records in the input layer. In some embodiments, the machine learning module 896 may propagate the input through the layers of the neural network to predict or forecast the optimal competitive set report 898 based on known and recorded search term metrics, and compare these predicted values ​​with the optimal search terms to be presented in the competitive set report 898. In some implementations, using a backpropagation method, the machine learning module 896 can then adjust the weight matrix of the neural network using the difference between the predicted value and the known optimal value, the weight matrix describing how changes in the data metric for each search term might affect the optimal search term to be presented in the competitive set report 898.

[0093] Using the output layer, computing device 822 can provide learned competitive search terms, which are determined as optimal search terms (if any search terms have been specified) and are based on similar and frequent search terms detected at the search engine 894 of digital marketplace 882 during use of computing device 822. These resulting learned optimal search terms can be recommended to the user or implemented automatically. In some implementations, the recommendations may include indicators and may be illustrated at a user interface (e.g., a graphical user interface) for user approval before implementing other processes executed by processor 810 of computing device 822.

[0094] Figure 9 The image shows an example representation of a graph. This example graph can indicate the position of each search term for competing products relative to the target product based on frequency. Figure 9 Each point (e.g., a circle) on the graph represents a search term. Each representative search term is... Figure 9 The graph is arranged at points that define the frequency with which a term appears alongside search terms for the target product, and at positions that indicate whether the search term is similar or dissimilar to search terms associated with the target product. In this example graph, the closer any given search term is to the right, the more similar the competitor's search term is to the target product's. Conversely, the closer any given search term is to the left, the less similar the competitor's search term is to the target product's. Furthermore, the closer any given search term is to the top of the graph, the more generic it is compared to the target product, while the closer any given search term is to the bottom of the graph, the more niche it is compared to the target product. In some implementations, it may be most desirable to have search terms associated with the target product that are more generic and similar to those associated with competitor products. This indicates that the target product is competing with relatively well-known competitors. The process described herein can help provide users with reports indicating how to adjust ad revenue to focus on more generic and similar search terms, similar to those associated with competitor products.

[0095] In some implementations, the machine learning module 896 can repeatedly perform forward and backward propagation using different input node values ​​to fine-tune any weighted or unweighted matrix. In some implementations, the machine learning module 896 can adaptively learn how changes in multiple sets of target product search terms and rankings, and multiple sets of competing product search terms and rankings, can affect the data reflected in the competition set report 898. In such implementations, the weight matrices associated with the layers of the neural network model can mathematically describe these relevances for a single target product. In some implementations, the neural network model (including the specification of node values ​​in the input layers and the number of layers), together with the weight matrices associated with each layer, can form a trained machine learning classifier, algorithm, or mathematical model to be used to generate any competition set report 898 described herein.

[0096] As described herein, the output from the already trained machine learning module 896 is a competition set report 898. Using the competition set report 898, computing device 822 can determine, via processor 810 and NID 880, the current performance of search terms most relevant to the target product and defined in the competition set report 898. Two variables identified in this process are the overall frequency of the term in searches (e.g., the total number of search terms, or the number of times people search for the term per day) and the frequency of the term in searches associated with the competition set report 898. More specifically, in some embodiments, those search terms considered most general and similar among the target product and each competing product are provided to comparison module 834, which searches for those search terms defined in the competition set report 898 via execution at search engine 894 by processor 810. During this process, processor 810 can access search engine 894 or any other search engine at digital marketplace 882 and obtain search term metadata describing the current performance of each search term most relevant to the target product and defined in the competition set report 898. Comparison module 834 can compare these most relevant search terms from competition set report 898 and provide this data to the user in the form of an actionable report 837. In some embodiments, the data describing the most relevant search terms to the target product and defined in the competition set of actionable report 837 can be provided to the user via a graphical representation.

[0097] Figure 10 The image shows an example graphical representation of the current performance of search terms related to the target product. For example... Figure 10As shown, the closer a search term (e.g., represented by a circle) is to the right of the graph, the higher its search volume or the more frequently it appears compared to other search terms, indicating a relatively high relevance to competing products. Conversely, the closer a search term is to the left of the graph, the lower its search volume or the less frequently it appears compared to other search terms, indicating a relatively low relevance to competing products. Furthermore, the closer a search term is to the top of the graph, the higher its relevance compared to other search terms, indicating a relatively high relevance to competing products. Additionally, the lower a search term is placed in the graph, the lower its relevance compared to other search terms, indicating a relatively low relevance to competing products. The most frequently searched and relevant terms can also be provided to the comparison module 834 and used to further define the sustainability and viable growth of the target product over time in, for example, the digital market 882.

[0098] With such Figure 10 The most relevant and frequent search terms indicated are found and presented in the actionable report 837. The computing device 822 can also quantify the opportunity that those search terms, when associated with the target product, will increase revenue and profit margin on the target product. In some implementations, the processor 810 can execute the revenue module 899 to receive the relevant and most frequent search terms from the actionable report 837 and provide output to the user in the form of an increased revenue metric. The revenue module can calculate the increased revenue during execution by the processor 810 using the following equation:

[0099] Increased revenue = increased exposure Click-through rate Conversion rate Number of orders price

[0100] Equation 1

[0101] In some implementations, within the context of Equation 1, exposure can be defined as the number of searches for each of the most relevant and frequent search terms. In some implementations, the number of exposures can be measured by the number of times an advertisement associated with the target product is presented to any given user during or after the most relevant and frequent search terms are entered into search engine 894. Processor 810 can retrieve this data by accessing a specific database or by accessing a search query website as described herein.

[0102] In some implementations, the click-through rate in Equation 1 can be defined as: an estimate along a curve of the probability of receiving a click associated with the ranking for each of the most relevant and frequent search terms provided in the actionable report 837. For example, the ranking can be set to include the first-place click-through rate (e.g., 20% of clicks), the second-place click-through rate (14% of clicks), up to the tenth-place click-through rate (6% of clicks), and extending to any number of rankings for the most relevant and frequent search terms. The processor 810 can retrieve this data by accessing a specific database or by accessing a search query website as described herein.

[0103] In some implementations, the conversion rate in Equation 1 can be defined as the percentage of the most relevant and frequent search terms that are clicked, associated with the target product, and converted into sales (e.g., resulting in sales of the target product). Processor 810 can retrieve this data by accessing a specific database or by accessing a search query website as described herein.

[0104] In some implementations, the basket size can be defined as the number of items purchased in each conversion. In some implementations, this number can be the average of multiple purchases. For example, if multiple conversions have been detected, processor 810 can calculate how many target products were purchased in any given time (e.g., the number placed in a shopping cart to be purchased in the digital marketplace 882). This value can be at least equal to 1 or greater. Similarly, processor 810 can retrieve this data by accessing a specific database or by accessing a search query website as described herein.

[0105] In some implementations, the price of the target product may be the manufacturer's suggested retail price. In some implementations, the quantitative value of the price in Equation 1 is the average price of the target product or other branded products resulting from the purchase across any number of digital marketplaces 882, minus any discounts or promotions associated with those sales. The processor 810 may retrieve this data by accessing a specific database, such as an access search query website as described herein, or by accessing sales data from a database maintained by the manufacturer of the target product.

[0106] In some implementations, any one of the exposure, click-through rate, conversion rate, order volume, and price values ​​in Equation 1 can be enhanced by a weight value. In this implementation, the weight value can either strengthen or weaken the effect of any of these values ​​in Equation 1 to better determine the seller's revenue increase or opportunity to increase revenue. Because actual real-time data is used in Equation 1, the seller of the target product or the user of computing device 822 can know in real time whether to leverage the increased product views or sales to increase the target product's visibility relative to any competitor's products.

[0107] In some implementations, the value associated with click-through rate (CTR) in Equation 1 can significantly alter the decision of the user of computing device 822 to take action (e.g., to provide more ads supporting the target product). In some implementations, the CTR associated with the following improvement in search ranking can be weighted to account for the increased importance of this value: an improvement in the target product's current position for a search term to a potential ranking position for a search phrase. For example, a given search term that could improve an organic search ranking for any search term from 20th to 5th would increase the CTR by an estimated 3x. The ranking improvement could also be partly due to increased exposure, particularly if the target product, which previously had no ranking for a search term, achieves a 10th search ranking. In this example, this would increase the number of clicks from zero (due to zero exposure) to the estimated number of clicks associated with a 10th ranking for that search term. As output, processor 810 can provide an increased revenue report 802 via revenue module 899, which describes how, if any, revenue related to the sale of the target product has increased.

[0108] In some cases, certain search terms may not be applicable to the target product, but could potentially increase revenue if applicable. In the context of advertising, these currently inapplicable search terms can be referred to as "unavailable." These unavailable search terms may be those that, for some reason, are at least initially irrelevant to the target product or have not yet been associated with it, because the platform data associated with digital marketplace 882 lacks data related to the target product. In some implementations, machine learning module 896 may also be trained and used to receive data related to the characteristics of the target product, the target product's current competitors, and the current state of the e-commerce search term algorithm to determine the "winnability" of search terms. The winnability of search terms can be defined as: the probability of winning each search term (e.g., associating the target product with the search term) at any given point in time, and the estimated cost of winning those search terms.

[0109] The winability inputs described herein can be used to train the machine learning module 896 to provide a winability report 804. Some inputs to this model include any number of inputs, and the description of certain types of inputs does not imply a limitation on the breadth of inputs that can be fed into the machine learning module 896 to obtain the winability report; these additional and different inputs are contemplated herein. By way of example, inputs may include the current and historical prices of both the target product and competing products. This historical pricing can be retrieved from one or more digital marketplaces 882 via the execution of the processor 810 and NID 880 described herein. In this particular example, the processor 810 may enable the NID 880 to access one or more digital marketplaces 882 via a wired (wired transmitter / receiver 840) or wireless (wireless transmitter / receiver 850) connection to find instances of the target product and competing products being sold and retrieve their historical pricing values.

[0110] Another input to the machine learning module 896 may include current review ratings and review counts, as well as historical review ratings and review counts, associated with the target product and competing products. This review rating and review count data can be retrieved from one or more digital marketplaces 882 via execution of the processor 810 and NID 880 described herein. Digital marketplaces 882 typically provide a GUI that allows consumers of the target and competing products to input text describing their experience with the target and competing products, as well as ranking assessments of those products in the form of a digital rating system or star rating system. In this particular example, the processor 810 may enable the NID 880 to access one or more digital marketplaces 882 via a wired or wireless connection and look up review ratings and review counts associated with the target and competing products being sold, and provide this review rating and review count data to the machine learning module 896.

[0111] Another input to the machine learning module 896 can include content similarity scores for any search terms related to the target product and competing products. In some implementations, these scores can be generated based on the provided data. Figure 9 In, for example, any given search term in Figure 9 The closer to the right side of the graph, the more similar the search terms of competing products are to those of the target product. In a specific example, Figure 9 The x-axis (bottom) of the graph or its associated data can be used to determine the similarity score. For example... Figure 9 As shown, the similarity score can be based on Figure 9The similarity score is a positive or negative score for the numerical ranking on the x-axis. In this example, the similarity score can be a positive or negative weight reflected in the winability report 804 provided by the processor 810 when executing the machine learning module 896. In this implementation, the processor 810 can again enable the NID 880 to access one or more digital marketplaces 882 via a wired or wireless connection and retrieve multiple sets of target product search terms and rankings, as well as multiple sets of competitor product search terms and rankings, associated with the target product and competing products being sold. This data is then provided to the machine learning module 896.

[0112] Furthermore, other inputs to the machine learning module 896 may include platform-specific information, such as the average best-selling rank (BSR) of any given digital marketplace 882 associated with the target product and any number of competing products. The BSR can vary across any given digital marketplace 882, but these rankings can be averaged across multiple digital marketplaces 882 to obtain the value. In this implementation, the processor 810 can again enable the NID 880 to access one or more digital marketplaces 882 via a wired or wireless connection and retrieve the BSR data. This data is then provided to the machine learning module 896.

[0113] Other inputs to the machine learning module 896 can include projected search volume and click distribution for search terms. Combining this type of data provided to the machine learning module 896, it is possible to generate... Figure 10 The expected search volume for search terms is retrieved from the data in the graph. This data, describing the frequency of any given search term appearing in searches associated with the target product and competing products, can be accessed by processor 810 and provided as input to machine learning module 896. Additionally, any click distribution describing the number of clicks received for any given search term can be accessed by processor 810 and NID 880 at search engine 894 in digital marketplace 882.

[0114] Further inputs to the machine learning module 896 may include historical changes in the ranking of search terms related to the target product and search phrase product. At any given time, the search engine 894 may exhibit fluctuations in terms of what is searched on the internet. These search terms may be ranked, and their historical rankings may change over time based on numerous social, political, environmental, and economic factors. This historical data can be retrieved from the search engine 894 by the processor 810 and NID 880 and fed to the machine learning module 896.

[0115] Another example input to the machine learning module 896 may include targeted advertising spending associated with a search term, where the search term is associated with a target product. This data can be maintained on any database accessible to the processor 810 of the computing device 822. In a particular embodiment, data describing the targeted advertising spending associated with a search term (which is associated with the target product) may be maintained by the seller of the target product in a private database, and the user of the computing device 822 may have secure access to that database. This type of data may also be provided to the machine learning module 896.

[0116] Using all these different types of data obtained by processor 810 via NID 880, machine learning module 896 can construct multiple mathematical models that provide a winability report 804, which describes the probability of winning each search term (e.g., associating the target product with the search term) at any given time and the estimated cost of winning those search terms. As with each machine learning module 896, it can be "taught" using the winability factors described herein. In some implementations, machine learning module 896 can implement one or more nonparametric and parametric learning techniques. For example, in some implementations, the machine learning module can use a hierarchical neural network topology to model the relationships between multiple sets of winability factors. In some implementations, such a neural network may include: an input layer (e.g., winability factors) comprising a set of known records of values ​​for each of these parameters, settings, indicators, and data metrics; and an output layer comprising a predicted winability report 804 based on the set of values ​​of the known records in the input layer. In some implementations, the machine learning module 896 can propagate the input through the layers of a neural network to predict or forecast the optimal winability of a search term based on known and recorded search term metrics, and compare these predictions with the optimal search term to be presented in the winability report 804. In some implementations, using backpropagation, the machine learning module 896 can then use the difference between the predictions and the known optimal values ​​to adjust the weight matrix of the neural network, which describes how changes in each search term data metric might affect the optimal search term to be presented in the winability report 804.

[0117] Using the output layer, computing device 822 can provide learned competitive search terms, which are determined to be optimal search terms (if search terms have been specified) and are based on winning search terms detected at search engine 894 of digital marketplace 882 or other databases during use of computing device 822. These learned optimal search terms can be recommended to the user or implemented automatically. In some embodiments, the recommendations may include indicators and may be illustrated at the user interface for user approval before implementing other processes executed by processor 810 of computing device 822.

[0118] In some implementations, the machine learning module 896 can repeatedly perform forward and backward propagation using different input node values ​​to fine-tune any weighted or unweighted matrix. In some implementations, the machine learning module 896 can adaptively learn how changes in winability factors can affect the data reflected in the winability report 804 in such a way. In such implementations, the weight matrices associated with the layers of the neural network model can mathematically describe these correlations for a single target product. In some implementations, the neural network model (including the specification of node values ​​in the input layers and the number of layers) together with the weight matrices associated with each layer can form a trained machine learning classifier, algorithm, or mathematical model to be used to generate any winability report 804 described herein.

[0119] As described herein, the output from the already trained machine learning module 896 is a winability report 804. Using the winability report 804, computing device 822 can determine the probability of achieving the desired change in income based on the required investment, via processor 810 and NID 880. In some implementations, the required investment can be calculated using the following equation:

[0120] Required investment = Expected bid (exposure) Click-through rate

[0121] Equation 2

[0122] The return on investment (ROI) can then be calculated using the following equation:

[0123] ROI = Increased Revenue (Stay within the expected timeframe for the required investment)

[0124] Equation 3

[0125] Using Equations 2 and 3, users can then prioritize advertising and search engine optimization actions for target products with search terms that have a high return on investment. In this way, computing device 822 can execute machine learning module 896 to achieve a second objective: determining the “winnability” of search terms while applying additional funds to advertising and search engine optimization.

[0126] In some implementations, the processor 810 may also perform advertising spend margin calculations, advertising spend potential calculations, and revenue potential calculations to specifically determine how much additional advertising funding should be applied to the target product. Similarly, the advertising spend margin can be calculated by multiplying the target ACoS by the price of the target product. The target ACoS can be determined and set by the seller based on available capital, or it can be set by the seller based on the percentage of revenue received from sales of the target product on the digital marketplace 382 to date and manufacturing costs. The advertising spend potential can then be calculated by multiplying the monthly opportunity unit (OU) by the spending margin. The monthly OU can be calculated based on the target product's click-through rate, which is the result of a sale of the target product after a buyer views the product. The revenue potential can then be calculated by multiplying the OU by the price of the target product. The revenue potential of each target product can be ranked to determine the placement of the target product in the digital marketplace 882. The search terms presented in the winability report 804 can be sorted by revenue potential to determine the best opportunity for revenue growth of the target product. To refine the recommendations, the process can continue to input estimated bid amounts from the digital marketplace 882 required to win ad placements for these keywords. In this way, the execution of processor 810 can initiate these calculations to predict the number of clicks and necessary costs required to achieve potential growth. The equation for performing this calculation is found by combining Equation 2 of this paper.

[0127] The ROI can be further calculated using the following equation:

[0128] ROI = Advertising Spending Potential (Return on Investment - Required Investment)

[0129] Equation 4

[0130] Because the process leverages both advertising and search engine optimization techniques to target highly winnable terms, increasing associated exposure, clicks, and conversion rates, the treatment applied to the target product can continuously adapt and adjust. As the target product succeeds on new search terms, the set of competing products defined in Competitive Set Report 898 shifts to comparisons with a larger and less niche set of competitors. As the set of competing products defined in Competitive Set Report 898 changes, so does the set of competing terms. With changes in reviews, terms, seller rankings, and other attributes, the winnability of each term and the associated required investment also change. As winnability shifts, new terms are prioritized, and the process iterates continuously to proportionally increase revenue associated with the target product.

[0131] In some embodiments, computing device 322 (e.g., and / or system 100, computing device 420, computing device 520, and / or computing device 822) may be configured to implement an automated latent machine learning system and method in accordance with the principles of this disclosure. For example, machine learning module 896 or another machine learning module may implement one or more models configured to receive various inputs related to advertising bids, determine targets (e.g., keywords, products, etc.) based on these inputs, and optimize bids for those targets. In these embodiments, machine learning module 896 may be implemented as an Automated Latent Machine Learning (ALML) module.

[0132] In the example, the machine learning module 896 receives inputs such as the product / product type to be advertised, the market (and / or advertising technology) on which the advertisement is to be placed, the expected expenditure (i.e., spending), the maximum allowed expenditure, the type of performance metric sought, the minimum performance required, and the risk threshold.

[0133] Expected spending can refer to average target spending, spending over a predetermined period (e.g., the amount expected to be spent over a period of time at a given rate, such as $100.00 per day), or a combination thereof. Maximum allowed spending can be a threshold corresponding to a hard budget cap for a given period in the system. For example, the system can stop spending in response to reaching this threshold, regardless of the size of the opportunity. The type of performance metric sought can include, but is not limited to, ROI or similar metrics, user impressions, product page traffic, new brand customers, etc. Minimum performance requirements inform the system not to pursue opportunities that produce performance below the minimum threshold.

[0134] In other examples, additional inputs may include, but are not limited to: OOS (Out of Stock) indications (e.g., outputs of systems, methods, etc., configured to monitor product availability); industry events (e.g., outputs of systems, methods, etc., configured to monitor major industry events—such as raw material shortages, product recalls, etc.); bid / budget changes (e.g., outputs of systems, methods, etc., configured to monitor bid or budget changes); holidays (e.g., programmable inputs indicating major holidays in different markets); winability scores; suppression, Buy Box, or featured offers. Changes in Offers (and / or similar functionality for various other applications), and / or seller information (e.g., outputs of systems, methods, etc., configured to monitor changes in the Buy Box / Special Offers for products, such as changes corresponding to suppression, seller changes, etc.); organic rankings (e.g., the organic ranking of a product in product-search term matching); social listening / trend analysis data (e.g., outputs of systems, methods, etc., configured to listen for available / developed social trends); seasonal data (e.g., seasonal trend analysis for products and search terms); product data (e.g., outputs of systems, methods, etc., configured to analyze the relationship between a product and a specific search term); and shopping basket data (e.g., outputs of systems, methods, etc., configured to perform complementary product analysis to place ads next to it).

[0135] Machine learning module 896 can implement one or more target determination models configured / trained to determine relevant targets (e.g., keyword targets, product targets, etc.). In the example, machine learning module 896 implements different models for different target types (e.g., separate keyword target determination models and product target determination models). The target determination models are configured to identify the targets most relevant to the advertised product (e.g., target products customers are willing to switch to) based on one or more inputs. The target determination models are configured to generate and output a ranking of targets, and provide a minimum relevance threshold for targets (e.g., potentially relevant targets).

[0136] In the example, the targeting model is configured to determine target relevance in part based on selected digital shelf space or selected keywords. Other inputs to the targeting model may include, but are not limited to: semantic comparisons of product descriptions for measuring keyword overlap, semantic comparisons of keywords for measuring product overlap, etc.

[0137] In this way, the output of the target determination module provides a list of relevant targets sorted by priority, as well as the minimum relevance to be considered as part of a potential target group.

[0138] Machine Learning Module 896 can implement an outage determination model, which is configured / trained to determine the probability of an outage for one or more products. An outage occurs when the main competitor regarding the target is no longer available or is impaired in some way. Examples of outages include, but are not limited to: advertising budget exhaustion or discontinuation outages (e.g., relevant competitor products have stopped advertising); stockout outages (e.g., relevant competitor products are out of stock); and detail page outages (e.g., relevant competitor products cannot be found through search or cannot be purchased directly from the marketplace for other reasons). Once any of these outages occur, an opportunity is created for the competitor product to become relevant and desirable.

[0139] In the example, to execute the interruption determination model, the machine learning module 896 is configured to collect data related to previously occurring historical interruptions and the current state of the interruptions. Relevant features / inputs include, but are not limited to: interruption hours, day of the week, date of the month, product category, keyword category, brand association, affected markets, affected regions, and the current state of each type of interruption. By combining both historical and current states, the machine learning module 896 executes the interruption determination model to predict both the probability and duration of interruptions based on these inputs and other inputs.

[0140] Machine Learning Module 896 implements a performance estimation model configured / trained to estimate expected performance output for a given bid or bid range. The performance estimation model predicts expected performance output (e.g., expected sales, new customers, traffic, impressions, etc.) based on: the output of the interruption determination model (e.g., interruption probability), the output of the target determination model, the performance of historical browsing latency (e.g., historical performance of expected output such as sales, new customers, traffic, impressions, etc.), and various other inputs (e.g., inputs similar to those of the interruption determination model). In this way, a machine learning model can be used to predict performance based on hypothetical bidding scenarios (e.g., a simplified scenario could be predicting expected output with a bid of $1.00 per click, a bid of $1.50 per click, etc.), where the expected performance will fall within the minimum limits set by the user. The performance estimation model predicts an estimate of expected performance for each of these bidding scenarios.

[0141] Machine Learning Module 896 can implement a cost estimation model configured / trained to estimate the cost of each objective given a bid or bidding scenario, bid range, etc. For example, the cost estimation model can have a similar structure to the performance estimation module (e.g., it can receive the same or similar inputs), but is modified to generate and output estimated costs instead of performance estimates. In some examples, combined cost and performance estimation models can be configured to output both performance and cost estimates. The estimated costs can be used to generate a series of predictions for each objective for different bidding scenarios or bid levels. For example, based on historical cost performance, product information, competitor information, and similar findings in the data, the model can predict both the expected value and the uncertainty of these predictions.

[0142] Therefore, computing device 822 is configured (e.g., using machine learning module 896 or other modules, models, etc.) to determine estimated performance and costs for a series of bidding scenarios, expected total expenditure, minimum performance target, and maximum allowed expenditure. Thus, bidding scenarios can be selected for each target to satisfy constraints such as minimum performance target constraints. Furthermore, a set or batch of bidding scenarios can be selected that sum to the expected total expenditure. If the maximum expenditure is reached over a period of time, advertising in the corresponding market can be automatically terminated. Each of these models implemented by machine learning module 896 can incorporate its own history (i.e., each model is continuously strengthened and learned over time as data is collected and market conditions change), and various default values ​​can be used when the required user input is lacking.

[0143] Other outputs of the model implemented by machine learning module 896 may include, but are not limited to: data indicating where to perform bid lurking (e.g., corresponding to recommendations on which ad networks to set up bid lurking / lurking); product recommendation data (e.g., recommendations for products for which bid lurking campaigns are set up); opportunity estimates (e.g., estimates of the boost that would result from performing bid lurking for a given product, market, etc.); and latency recommendation data (e.g., the time / slot for which recommendations are used to activate or deactivate bid lurking). In some examples, computing device 822 includes / implements a recommendation engine configured to generate alerts indicating opportunities to reduce spending on keywords (e.g., by disabling standard campaigns and enabling browsing lurking).

[0144] Therefore, the systems and methods disclosed herein help avoid advertising bidding wars and rising advertising costs, while maximizing performance objectives by seizing opportunities on relevant and winnable targets. These systems and methods reduce costs by pursuing bidding opportunities at the lowest possible cost, increase efficiency by requiring minimal human input and monitoring, maximize performance based on various performance and expenditure constraints, and continuously improve over time without human intervention.

[0145] Figure 11 This is a flowchart generally illustrating a method 1100 for automated latency (e.g., in an advertising bidding environment) based on the principles of this disclosure. Method 1100 may be implemented by one or more processors or processing devices, computing devices, etc., as described herein. For illustrative purposes, method 1100 will be described as being implemented by computing device 822. As an example, computing device 822 implements method 1100 by executing one or more machine learning modules or models (e.g., machine learning module 896 incorporating various models described herein). In various other examples, all or part of method 1100 may be executed by one or more computing devices in network 100, computing devices implemented as smartphone 126 or other mobile devices, computing devices implemented as desktop computer 122 and / or server 152, etc.

[0146] At 1104, method 1100 receives various inputs related to bid potential, including but not limited to: the product / product type to be advertised, the market, expected spending, maximum allowed spending, the type of performance metric sought, minimum performance requirements, risk thresholds, etc. For example, inputs may be received at the processor 810 or other components of computing device 822 via user input 860, data storage 830, network interface device 880, etc.

[0147] At 1106, method 1100 computes (e.g., using a target determination model implemented by machine learning module 896 in some examples) one or more product and / or keyword targets based on the received input. In the example, method 1100 computes a ranking of targets and a minimum relevance threshold for the targets. For example, processor 810 executes the target determination model based on the input received at 1104.

[0148] At 1108, method 1100 calculates (e.g., using an interruption determination model implemented by machine learning module 896 in some examples) one or more interruption probabilities for one or more products (e.g., the products identified at 1104). For example, processor 810 may receive inputs, including but not limited to: data related to previously occurring historical interruptions, interruption hours, days of the week, dates in months, product categories, keyword categories, brand associations, affected markets, affected regions, etc., and execute the interruption determination model to predict the interruption probabilities based on these and other inputs.

[0149] At 1112, method 1100 computes (e.g., using a performance estimation model implemented by machine learning module 896 in some examples) an estimate of the expected performance output for a given bid or bid range. For example, method 1100 (e.g., processor 810) computes a performance prediction (e.g., for the expected performance metric) for each of multiple bidding scenarios, based on the output of the interruption determination model obtained at 1108, the output of the target determination model obtained at 1106, the performance of historical browsing latent activity, etc.

[0150] At 1116, method 1100 calculates (e.g., using a cost estimation model implemented by machine learning module 896 in some examples) an estimate of the cost per target for a given bid or bid range. For example, method 1100 (e.g., processor 810) calculates an estimate of the cost per target for each of multiple bidding scenarios, based on the output of the interruption determination model obtained at 1108, the output of the target determination model obtained at 1106, the performance of historical browsing activity, etc. In various examples, method 1100 may include only one or both of steps 1112 and 1116.

[0151] At 1120, method 1100 generates output based on the results obtained at 1106, 1108, 1112, and / or 1116, said output being used to control various performance parameters of bid latency. The output includes, but is not limited to: estimated performance and cost, expected total expenditure, minimum performance target, maximum allowable expenditure, etc. For example, processor 810 provides the output of various models and other calculations to components configured to implement various automated bid latency processes and functions. In one example, processor 810 and / or other components of the computing device are configured to implement all or part of the automated bid latency process. In another example, computing device 822 provides output (e.g., via user output 870, network interface device 880, etc.) to one or more computing devices external to computing device 822, such as server 852.

[0152] At 1124, method 1100 executes and controls one or more bid-latency activities based on the output generated at 1120 (e.g., an automated bid-latency process configured to latinate and execute bids in an advertising bidding environment). For example, executing and controlling bid-latency may include, but is not limited to, controlling and / or enabling one or more computing devices to bid on products / keywords within the constraints and bidding parameters obtained in steps 1104 through 1120, such constraints and bidding parameters being, for example, data indicating where to execute bid-latency, product recommendation data, opportunity estimates, latency recommendation data, etc.

[0153] In one example, one or more computing devices external to computing device 822 (e.g., server 852 or any other server implementing the digital marketplace 882, search engine 894, etc., as described herein) control the automated bid-latency process. In various examples, controlling the bid-latency process may include dynamically (e.g., in real-time or near real-time) exchanging data between computing device 822 and one or more external computing devices, such as updating various inputs, outputs, etc. For example, one or more external computing devices may provide computing device 822 with data acquired during the bid-latency process, and computing device 822 may perform functions based on the data, such as generating alerts, indicating an increase or decrease in the chance of keyword spending.

[0154] Any method disclosed herein includes one or more steps or actions for performing the described method. Method steps and / or actions may be interchanged with each other. In other words, the order and / or use of specific steps and / or actions may be modified unless proper operation of the implementation requires a specific order of steps or actions.

[0155] The use of the term "first" in the claims regarding features or elements does not necessarily imply the presence of a second or additional such feature or element. Elements described in the form of means plus function are intended to be interpreted according to paragraph 6 of 35 USC §112. It will be apparent to those skilled in the art that changes may be made to the details of the above embodiments without departing from the fundamental principles of this disclosure.

[0156] The foregoing discussion is intended to illustrate the principles and various implementations of this disclosure. Once the foregoing disclosure is fully understood, many variations and modifications will become apparent to those skilled in the art. The appended claims are intended to be construed as encompassing all such variations and modifications.

[0157] The word “example” as used herein means intended as an example, instance, or illustration. Any aspect or design described herein as an “example” is not necessarily to be construed as preferred or advantageous over other aspects or designs. Rather, the use of the word “example” is intended to present the concept in a specific manner. As used herein, the term “or” means inclusive rather than exclusive. That is, unless otherwise stated or clearly indicated by the context, “X comprises A or B” refers to any natural substitution of inclusion. That is, if X comprises A; X comprises B; or X comprises both A and B, then “X comprises A or B” is satisfied in any of the foregoing cases. Additionally, unless otherwise stated or clearly indicated by the context, the articles “a” and “an” as used herein and in the appended claims should generally be construed as meaning “one or more”. Furthermore, unless so described, the use of the terms “implementation” or “an implementation” throughout the document does not refer to the same implementation or mode of implementation.

[0158] The systems, algorithms, methods, instructions, etc., described herein can be implemented in hardware, software, or any combination thereof. Hardware may include, for example, a computer, intellectual property (IP) core, application-specific integrated circuit (ASIC), programmable logic array, optical processor, programmable logic controller, microcode, microcontroller, server, microprocessor, digital signal processor, or any other suitable circuit. In the claims, the term "processor" should be understood to cover any of the foregoing hardware, individually or in combination. The terms "signal" and "data" are used interchangeably.

[0159] As used herein, the term "module" can include packaged functional hardware units designed for use with other components, instruction sets executable by a controller (e.g., processors executing software or firmware), processing circuitry systems configured to perform specific functions, and self-contained hardware or software components that interface with a larger system. For example, a module can include application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), circuits, digital logic circuits, analog circuits, combinations of discrete circuits, gates, and other types of hardware or combinations thereof. In other embodiments, a module can include a memory storing instructions that can be executed by a controller to implement the features of the module.

[0160] Furthermore, in one aspect, for example, the system described herein may be implemented using a general-purpose computer or general-purpose processor having a computer program that, when executed, performs any of the corresponding methods, algorithms, and / or instructions described herein. Alternatively or alternatively, for example, a special-purpose computer / processor may be utilized, which may include additional hardware for performing any of the methods, algorithms, or instructions described herein.

[0161] Furthermore, all or part of the implementation of this disclosure may take the form of a computer program product accessible, for example, from a computer-usable or computer-readable medium. A computer-usable or computer-readable medium may be any device capable of tangibly containing, storing, transmitting, or transporting a program used by or in combination with any processor. The medium may be, for example, an electronic, magnetic, optical, electromagnetic, or semiconductor device. Other suitable media are also available.

[0162] The above-described embodiments, implementations, and aspects have been provided to facilitate a clear understanding of this disclosure, but are not intended to limit it. Rather, this disclosure is intended to cover all modifications and equivalent arrangements included within the scope of the appended claims, which should be interpreted in the broadest possible sense to encompass all such modifications and equivalent structures permitted by law.

Claims

1. A system configured to control the bid latency process in an advertising bidding environment, the system comprising: processor; as well as The memory includes instructions that, when executed by the processor, cause the processor to: Receive input, wherein the input includes data indicating at least one of the following: the product to be advertised, the type of product to be advertised, the market for advertising the product or product type, the expected expenditure amount for advertising the product or product type, the maximum expenditure amount for advertising the product or product type, the type of performance metric associated with advertising the product or product type, the minimum required performance metric associated with advertising the product or product type, and the risk threshold associated with advertising the product or product type. Calculate at least one of the product target and keyword target based on the input. Calculate the interruption probability of the product associated with at least one of the product target and the keyword target. Based on the received input, calculate (i) a prediction of the performance output of at least one bid to be executed for the bid latency process, and (ii) an estimate of the cost for each objective of the at least one bid. The bidding latency process is controlled to selectively execute bids on at least one of the product target and the keyword target based on (i) the calculated probability, (ii) the prediction of the performance output, and (iii) the cost estimate of each target.

2. The system of claim 1 further includes an automated latent machine learning module, the automated latent machine learning module being configured to perform the bid latent process in response to the processor.

3. The system according to claim 1, wherein, The expected expenditure amount includes at least one of the average target expenditure and the expenditure within a predetermined time period.

4. The system according to claim 1, wherein, The performance metrics include at least one of the following: return on ad spend, user impressions, product page traffic, and new brand customers.

5. The system according to claim 1, wherein, The minimum performance requirement metric is the minimum performance threshold.

6. The system according to claim 1, wherein, The inputs also include at least one of the following: out-of-stock indications, industry events, bid changes, budget changes, holidays, winability scores, suppression, special offer changes, seller information, organic rankings, social listening or trend analysis data, seasonal data, product data, and shopping basket data.

7. The system according to claim 1, wherein, The processor is further configured to implement a target determination model, which is trained to: in order to calculate at least one of the product target and the keyword target, identify the product target and the keyword target that are most relevant to the product to be advertised.

8. The system according to claim 7, wherein, The target determination model is configured to generate and output (i) the ranking of at least one of the product targets and the keyword targets, and (ii) the minimum relevance threshold of the targets.

9. The system according to claim 7, wherein, The target determination model is configured to determine the relevance of the product target and the keyword target based on at least one of selected digital shelves, selected keywords, and semantic comparisons of product descriptions.

10. The system according to claim 7, wherein, The processor is also configured to implement an interrupt determination model, which is trained to calculate the interrupt probability of the product.

11. The system according to claim 10, wherein, The interruption determination model is trained to calculate the interruption probability of the product based on data related to the product's historical interruptions.

12. The system according to claim 10, wherein, The processor is also configured to implement a performance estimation model, which is trained to compute a prediction of the performance output for the at least one bid based on the output of at least one of the target determination model and the interruption determination model.

13. The system according to claim 10, wherein, The processor is also configured to implement a cost estimation model, which is trained to calculate an estimate of the cost for each of the at least one bid by generating a series of predictions for different bid levels for at least one of the product target and the keyword target.

14. A method for controlling an automated bid latency process in an advertising bidding environment, the method comprising: Using one or more computing devices, Receive input, wherein the input includes data indicating at least one of the following: the product to be advertised, the type of product to be advertised, the market for advertising the product or product type, the expected expenditure amount for advertising the product or product type, the maximum expenditure amount for advertising the product or product type, the type of performance metric associated with advertising the product or product type, the minimum required performance metric associated with advertising the product or product type, and the risk threshold associated with advertising the product or product type; Calculate at least one of the product objective and the keyword objective based on the input; Calculate the interruption probability of the product associated with at least one of the product target and the keyword target; Based on the received input, calculate (i) a prediction of the performance output of at least one bid to be executed for the bid latency process, and (ii) an estimate of the cost for each objective of the at least one bid; and The bidding latency process is controlled to selectively execute bids on at least one of the product target and the keyword target based on (i) the calculated probability, (ii) the prediction of the performance output, and (iii) the cost estimate of each target.

15. The method of claim 14, comprising at least one of the following: The expected expenditure amount includes at least one of the average target expenditure and the expenditure within a predetermined time period; The performance metrics include at least one of the following: ROI (Return on Ad Spend), user impressions, product page traffic, and new brand customers; and The minimum performance requirement metric is the minimum performance threshold.

16. The method of claim 14, wherein, The inputs also include at least one of the following: out-of-stock indications, industry events, bid changes, budget changes, holidays, winability scores, suppression, special offer changes, seller information, organic rankings, social listening or trend analysis data, seasonal data, product data, and shopping basket data.

17. The method according to claim 14, wherein, Calculating at least one of the product objective and the keyword objective includes at least one of the following: (i) identifying at least one of the product objective and the keyword objective that is most relevant to the product to be advertised; (ii) generating and outputting a ranking of at least one of the product objective and the keyword objective; (iii) generating and outputting a minimum relevance threshold for the objective; and (iv) determining the relevance of at least one of the product objective and the keyword objective based on at least one of a semantic comparison of featured digital shelf, featured keywords, and product description.

18. The method of claim 17, further comprising calculating the interruption probability of the product based on data related to historical interruptions of the product.

19. The method of claim 18, further comprising calculating an estimate of the cost for each of the at least one bid by generating a series of predictions for different bid levels for the product target and the keyword target.

20. A processor configured to execute instructions stored in memory, the instructions being used to control an automated bid latency process in an advertising bidding environment, wherein, When the instruction is executed by the processor, the processor: Receive input, wherein the input includes data indicating at least one of the following: the product to be advertised, the type of product to be advertised, the market for advertising the product or product type, the expected expenditure amount for advertising the product or product type, the maximum expenditure amount for advertising the product or product type, the type of performance metric associated with advertising the product or product type, the minimum required performance metric associated with advertising the product or product type, and the risk threshold associated with advertising the product or product type; Calculate at least one of the product objective and the keyword objective based on the input; Calculate the interruption probability of the product associated with at least one of the product target and the keyword target; Based on the received input, calculate (i) a prediction of the performance output of at least one bid to be executed for the bid latency process, and (ii) an estimate of the cost for each objective of the at least one bid; and The bidding latency process is controlled to selectively execute bids on at least one of the product target and the keyword target based on (i) the calculated probability, (ii) the prediction of the performance output, and (iii) the cost estimate of each target.

Images