Method and system for providing display conversion optimization and readable medium

Abstract

Systems, methods, and non-transitory computer readable media for display transformation optimization are disclosed. A display transformation estimation and optimization system receives a set of list data for generating a display of items sold on an online marketplace, and determines a likelihood value indicative of a likelihood that the display will result in a sale within a given time period based on the set of list data. The display transformation estimation and optimization system causes a graphical indicator representing the likelihood value to be presented on a display of a client device of the display user.

Description

[0001] This application is a divisional application of the Chinese invention patent application with application number 202110149522.8, application date February 3, 2021, and invention name “Display Conversion Estimation and Optimization”. Technical Field

[0002] Implementations of the present subject matter relate generally to generating displays, and more particularly, to display conversion estimation and optimization. Background Art

[0003] Online marketplace services allow users to buy and sell items. For example, these services enable users to post listings for each item that the user wishes to sell, as well as view listings posted by other users. Although these types of services make it easy to buy and sell items, they also provide challenges. Sellers do not interact directly with customers in an online setting, and therefore may not be aware of items that are currently in demand. This may make some users reluctant to list items for sale because they do not want to waste time creating listings for items that are unlikely to sell. In addition, sellers may not be sure what information to include in the listing will increase the likelihood that the listed item will sell. Therefore, improvements are needed. Summary of the invention

[0004] The present invention provides a method, which includes: receiving a first set of listing data from a client device for generating a display of items for sale on an online market; based on the first set of listing data, determining a first likelihood value indicating the likelihood that the display will result in a sale within a given time period; and causing a graphical indicator to be presented on a display of the client device, the graphical indicator representing the first likelihood value.

[0005] The present invention provides a system, which includes: one or more computer processors; and one or more computer-readable media storing instructions, which, when executed by the one or more computer processors, cause the system to perform operations, including: receiving a first set of listing data from a client device for generating a display of items for sale on an online market; based on the first set of listing data, determining a first likelihood value indicating the likelihood that the display will result in a sale within a given time period; and causing a graphical indicator to be presented on a display of the client device, the graphical indicator representing the first likelihood value.

[0006] The present invention provides a non-transitory computer-readable medium storing instructions that, when executed by one or more computer processors of one or more computing devices, cause the one or more computing devices to perform operations, the operations comprising: receiving a first set of listing data from a client device for generating a display of items for sale on an online marketplace; determining, based on the first set of listing data, a first likelihood value indicating the likelihood that the display will result in a sale within a given time period; and causing a graphical indicator to be presented on a display of the client device, the graphical indicator representing the first likelihood value. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] In the accompanying drawings, which are not necessarily drawn to scale, the same reference numerals may describe similar components in different views. The same reference numerals with different letter suffixes may represent different instances of similar components. Some embodiments are shown in the figures of the accompanying drawings by way of example and not limitation, in which:

[0008] Figure 1 A system providing display conversion estimation and optimization is shown according to some example implementations.

[0009] Figure 2 is a block diagram of an exhibition conversion estimation and optimization system according to some example implementations.

[0010] Figure 3 is a block diagram of a likelihood value determination module according to some example implementations.

[0011] 4A to 4H An example of a display interface providing display conversion estimation and optimization is shown according to some example embodiments.

[0012] Figure 5 is a flow chart illustrating a method of providing exhibition conversion estimates according to some example embodiments.

[0013] Figure 6 is a flow chart illustrating a method of providing display conversion optimization according to some example implementations.

[0014] Figure 7 is a block diagram illustrating a representative software architecture that may be used in conjunction with the various hardware architectures described herein.

[0015] Figure 8 is a block diagram illustrating components of a machine capable of reading instructions from a machine-readable medium (eg, a machine-readable storage medium) and performing any one or more of the methodologies discussed herein, according to some example embodiments. DETAILED DESCRIPTION

[0016] In the following description, for purposes of explanation, various details are set forth in order to provide a thorough understanding of some example embodiments. However, it will be apparent to one skilled in the art that the subject matter may be practiced without these specific details or with minor modifications.

[0017] References in the specification to "one embodiment" or "an embodiment" mean that a particular feature, structure, or characteristic described in conjunction with the embodiment is included in at least one embodiment of the subject matter. Thus, the appearances of the phrases "in one embodiment" or "in an embodiment" in various places throughout the specification do not necessarily all refer to the same embodiment.

[0018] For the purpose of illustration, specific configurations and details are set forth to provide a thorough understanding of the subject matter. However, it will be apparent to one of ordinary skill in the art that the embodiments of the described subject matter may be practiced without the specific details presented herein or in various combinations as described herein. In addition, well-known features may be omitted or simplified so as not to make the described embodiments unclear. Various examples may be given throughout the specification. These examples are merely descriptions of specific embodiments. The scope or meaning of the claims is not limited to the examples given.

[0019] Systems, methods, and non-transitory computer-readable media for display conversion estimation and optimization are disclosed. An online marketplace service allows users to buy and sell items online. For example, an online marketplace service allows users to post displays to an online marketplace that lists items for sale. Other users can view the posted displays and purchase the listed items if desired. As previously described, some sellers may be discouraged from posting displays if / when the seller is uncertain about the likelihood that a display will result in a conversion, such as the likelihood of selling the listed items. Additionally, some sellers may not be sure how they can increase the likelihood that a listed item will result in a conversion.

[0020] To mitigate these problems, the online marketplace service can improve the likelihood that a display will result in a conversion (e.g., a sale) by utilizing the functionality of a display conversion estimation and optimization system that determines the likelihood that a display will result in a conversion and provides suggested modifications. The display conversion estimation and optimization system can receive listing data input by a seller that generates a display and use the listing data to determine a likelihood value that indicates the likelihood that the display will result in a conversion during a specified time period. The display conversion estimation and optimization system can generate a graphical indicator, such as a graphical gauge, that represents the likelihood value and cause the graphical indicator to be presented to the seller that generated the display. The seller can use the graphical indicator to quickly and easily determine the likelihood that the display will result in a conversion.

[0021] The display conversion estimation and optimization system can update the likelihood values ​​and graphical indicators in real time or near real time during the display creation process. For example, the display conversion estimation and optimization system can receive updated listing data as the seller adds, modifies, and or deletes listing data. Examples of updated listing data can include additions and / or modifications to the display's description, title, price, image, features, etc. The display conversion estimation and optimization system uses the received updated listing data to determine an updated likelihood value that indicates the likelihood that the display will result in a conversion based on the modifications made to the display. The display conversion estimation and optimization system generates an updated graphical indicator representing the updated likelihood value and then presents the updated graphical indicator to the seller. Thus, a continuously updated representation of the likelihood that the display will result in a conversion is provided to the seller as the user adds, modifies, and / or removes listing data during the display creation process.

[0022] The display conversion estimation and optimization system can also provide the seller with suggested modifications to increase the possibility of the display leading to conversion. For example, the display conversion estimation and optimization system can determine the impact that a set of modifications such as adding additional data to the display, modifying existing data contained in the display, and / or removing existing data contained in the display may have on the possibility of the display leading to conversion. Then, the display conversion estimation and optimization system can provide the seller with the suggested modifications, which are estimated to have the greatest impact on the possibility that the display will lead to conversion. The suggested modifications can be presented to the seller together with the following instructions, which are instructions for the estimated impact of the possibility that the display will lead to conversion by executing the suggested modifications. For example, the suggested modifications can notify the seller that executing the suggested modifications can increase the possibility of the display leading to a specified amount of conversion and / or will lead to an updated probability value of a specified amount. Therefore, the seller can easily determine what modifications will improve the display and the impact that executing each modification will have on the possibility of the display leading to conversion.

[0023] Figure 1A system 100 for providing display conversion estimation and optimization according to some example embodiments is shown. As shown, multiple devices (i.e., client device 102, client device 104, online market service 106, and display conversion estimation and optimization 108) are connected to a communication network 110 and are configured to communicate with each other using the communication network 110. The communication network 110 is any type of network, including a local area network (LAN) such as an intranet, a wide area network (WAN) such as the Internet, or any combination thereof. In addition, the communication network 110 can be a public network, a private network, or a combination thereof. The communication network 110 is implemented using any number of communication links (including one or more wired communication links, one or more wireless communication links, or any combination thereof) associated with one or more service providers. In addition, the communication network 110 is configured to support the transmission of data formatted using any number of protocols.

[0024] A plurality of computing devices may be connected to the communication network 110. A computing device is any type of general-purpose computing device capable of network communications with other computing devices. For example, a computing device may be a personal computing device such as a desktop or workstation, a business server, or a portable computing device such as a laptop, smartphone, or tablet personal computer (PC). A computing device may include Figure 8 Some or all of the features, components, and peripherals of machine 800 are shown.

[0025] To facilitate communication with other computing devices, the computing device includes a communication interface that is configured to receive information such as requests, data, etc. from another computing device in network communication with the computing device and pass the information onward to an appropriate module running on the computing device. The communication interface also sends information to another computing device in network communication with the computing device.

[0026] In system 100, users interact with online marketplace service 106 to utilize services provided by online marketplace service 106. Online marketplace system 106 provides an online marketplace in which users can post items for sale and purchase items posted for sale by other users. For example, online marketplace service 160 may include items that are auctioned for sale and / or items that are listed for sale at a set price. Users communicate with online marketplace service 106 and utilize the functionality of online marketplace service 106 by using client devices 102 and 104, which are connected to communication network 110 through direct and / or indirect communication.

[0027] Although the system 100 shown includes only two client devices 102, 104, this is for ease of illustration only and is not intended to be limiting. Those skilled in the art will appreciate that the system 100 may include any number of client devices 102, 104. In addition, the online market system 106 may accept connections from any number of client devices 102, 104 in parallel and interact with these client devices. The online market system 106 supports connections from a variety of different types of client devices 102, 104, such as desktop computers; mobile computers; mobile communication devices such as mobile phones, smart phones, tablet computers; smart TVs; set-top boxes; and / or any other network-enabled computing devices. Therefore, the client devices 102 and 104 may have different types, capabilities, operating systems, etc.

[0028] The user interacts with the online market service 106 via a client-side application installed on the client devices 102 and 104. In some embodiments, the client-side application includes a component dedicated to the online market service 106. For example, the component can be a stand-alone application, one or more application plug-ins and / or a browser extension. However, the user can also interact with the online market system 106 via a third-party application such as a web browser, which resides on the client devices 102 and 104 and is configured to communicate with the online market service 106. In either case, the client-side application presents a user interface (UI) for the user to interact with the online market service 106. For example, the user interacts with the online market service 106 via a client-side application integrated with a file system or via a web page displayed using a web browser application.

[0029] The online market service 106 is one or more computing devices configured to facilitate an online market (e.g., EBAY, AMAZON, etc.) in which users can post items for sale and purchase items posted for sale by other users. For example, the online market service 106 provides a user interface that enables users to view listings posted to the online market service 106. Each listing provides details of one or more items listed for sale. For example, a listing may include an item description, an image, a sale price, a current bid price, a remaining auction time, shipping options, features, etc.

[0030] The online marketplace service 106 may also provide functionality that enables users to purchase and / or bid on items listed for sale. For example, the online marketplace service 106 may provide user interface elements (e.g., buttons, text fields, etc.) that users may use to select items to purchase, place bids, etc., and to provide their financial information (e.g., credit card number, bank account number) and personal information (e.g., shipping address, billing address, etc.) to complete the purchase.

[0031] In order to list items for sale on the online market, a user creates a user account using the online market service 106. The user account may include the user's personal information (e.g., name, address, email address, phone number, etc.) and financial information (e.g., credit card information, bank account information, etc.). Once the user has created the user account, the user may use the functionality of the online market service 106 using their user account, including listing items for sale on the online market. The online market service 106 provides a display interface to the user, which enables the user to create a new display and provide data for the display. For example, the display interface may include data fields that prompt the user to provide specified information for the display, such as a selling price, item description, listing title, image, shipping cost, return policy, features, etc. The display interface may also include user interface elements such as buttons that enable the user to submit and / or publish a complete list. That is, the user may publish the display after the user has filled in the data fields and has provided an image included in the display interface.

[0032] To assist users with listing processing, the online market service 106 provides display conversion estimation and optimization. For example, the online market service 106 can utilize the functionality of the display conversion estimation and optimization system 108. Although the display conversion estimation and optimization system 108 and the online market 106 are shown as separate entities, this is only for ease of explanation and is not meant to be limiting. In some embodiments, the display conversion estimation and optimization system 108 is incorporated as part of the online market service 106.

[0033] The display conversion estimation and optimization system 108 determines the likelihood that the display will result in a conversion, and provides suggested modifications to improve the likelihood that the display will result in a conversion. A conversion can be any type of desired action, such as selling a listed item, choosing to follow a listing, a specified number of item views, a specified number of item likes, etc.

[0034] The display conversion estimation and optimization system 108 can receive listing data input by a seller generating a display, and use the listing data to determine a likelihood value indicating the likelihood that the display will result in a conversion during a specified time period. The listing data can include any type of data provided to describe the listed item and / or the conditions associated with purchasing the listed item. For example, the listing data can include a listing title, item sale price, item description, images, shipping conditions and / or costs, return policy, features, etc.

[0035] When a user is generating a new display to be published to the online marketplace, the display conversion estimation and optimization system 108 may receive listing data from the online marketplace service 106. That is, the display conversion estimation and optimization system 108 may receive listing data while the user is using the display interface to enter text, upload images, select configurations, features, etc.

[0036] The display conversion estimation and optimization system 108 generates the likelihood value using one or more machine learning models trained on historical listing data. The historical listing data includes data associated with previous displays posted to the online marketplace. For example, the historical listing data includes listing data provided by sellers for listings previously posted to the online marketplace, such as listing titles, images, item descriptions, prices, features, etc. The historical listing data also includes performance data that describes interactions related to the display when the display is actively posted to the online marketplace. For example, the performance data may include data indicating whether the display resulted in a conversion (e.g., the listed item was sold), the number of days the display was active before the conversion, the number of times the display was viewed, the number of likes the display received, etc. The historical listing data may also include data describing the active inventory of the online marketplace during the time when the display was active, such as data describing the number of other active displays of the same item, the number of searches performed on the listed item, etc.

[0037] Once trained, the one or more machine learning models may output a likelihood value for a display based on a specified set of input data, such as the listing data provided for the display, the number of other active displays of the same item, the number of searches for the item, etc. Thus, the display conversion estimation and optimization system 108 collects input data and uses it as input into the one or more generated machine learning models, which in turn output a likelihood value for the display.

[0038] The likelihood value is a single value that indicates the likelihood that the display will result in a conversion within a given time period (e.g., 1 day, 1 week, 2 weeks, etc.). In some implementations, the likelihood value is determined based on a plurality of sub-values. For example, the likelihood value can be determined based on a sub-value indicating the likelihood that the display will result in a conversion based on the listing data, and a sub-value indicating the likelihood that the item will result in a conversion based on other active displays of the same item, and / or the number of searches for the display (e.g., inventory and / or demand for the item).

[0039] The display conversion estimation and optimization system 108 can generate a graphical indicator such as a graphical instrument or dial representing the likelihood value. The graphical indicator can facilitate the visual representation of the read likelihood value. For example, the graphical indicator can be a graphical dial that shows a pointer at a point representing the likelihood value. The graphical indicator can also present a color or other indicator to represent the likelihood value or the range in which the likelihood value is located. For example, the graphical indicator can present colors such as green, yellow, and red to indicate the range in which the likelihood value falls. Therefore, the user can view the needle to determine the likelihood value itself and the color presented to further understand the meaning of the likelihood value, for example, the meaning of the likelihood value representing a relatively high or low likelihood of the display leading to a conversion.

[0040] The display conversion estimation and optimization system 108 causes the graphical indicator to be presented to the seller who generated the display. For example, the graphical indicator can be presented within the display interface used by the user to generate the display. Therefore, the seller can use the presented graphical indicator to quickly and easily determine the likelihood that the display will result in a conversion.

[0041] The display conversion estimation and optimization system 108 can update the likelihood values ​​and graphical indicators in real time or nearly real time. For example, the display conversion estimation and optimization system 108 can receive updated listing data as the seller continues to generate new displays by adding, modifying, and / or removing listing data. Examples of updated listing data may include additions and / or modifications to the display's description, title, price, image, features, shipping conditions, etc. The display conversion estimation and optimization system 108 uses the received updated listing data to determine an updated likelihood value based on updates to the display. The display conversion estimation and optimization system 108 updates the graphical indicators presented to the seller based on the updated likelihood values. Thus, a continuously updated representation of the likelihood that the display will result in a conversion is provided to the seller as the user modifies the display.

[0042] The display conversion estimation and optimization system 108 can also provide suggested modifications to the seller to increase the likelihood that the display will result in a conversion. For example, the display conversion estimation and optimization system 108 can determine the impact that a set of modifications may have on the likelihood that the display will result in a conversion, such as adding additional data to the display, modifying existing data contained in the display, and / or removing existing data contained in the display. The display conversion estimation and optimization system 108 can then provide the seller with the suggested modifications that are estimated to have the greatest impact on the likelihood that the display will result in a conversion. For example, the suggested modifications can be presented to the user within the display interface.

[0043] The suggested modifications may be presented to the seller along with an indication of the impact that executing the suggested modifications will have on the estimated likelihood that the display will result in conversions. For example, the suggested modifications may inform the seller that executing the suggested modifications may increase the likelihood that the display will result in a specified amount of conversions and / or will result in an updated likelihood value of a specified amount. Thus, the seller may easily determine what modifications will improve the display, as well as the impact that executing each modification will have on the likelihood that the display will result in conversions.

[0044] Figure 2 is a block diagram of an exhibition conversion estimation and optimization system 108 according to some example embodiments. In order to avoid obscuring the subject matter of the present invention with unnecessary detail, the following has been described. Figure 2 Various functional components (e.g., modules) that are not relevant to conveying an understanding of the subject matter of the present invention are omitted. However, a skilled person will readily recognize that various additional functional components may be supported by the image suggestion platform 108 to facilitate additional functions not specifically described herein. In addition, Figure 2 The various functional modules depicted in the can reside on a single computing device, or can be distributed across several computing devices in various arrangements, such as those used in a cloud-based architecture. For example, the various functional modules and components can be distributed among computing devices that facilitate both the display conversion estimation and optimization system 108 and the online marketplace service 106.

[0045] As shown, the display conversion estimation and optimization system 108 includes a listing data access module 202 , a likelihood value determination module 204 , a graphical indicator generation module 206 , a suggestion generation module 208 , an output module 210 , and a data store 212 .

[0046] The listing data access module 202 accesses the listing data provided for the new display. For example, a user may use a display interface provided by the online market service 106 to enter text and / or upload images to generate a new display, and the listing data access module 202 may access the entered listing data. This may be performed when the user enters the listing data and / or at set intervals.

[0047] The listing data access module 202 may receive listing data from the online marketplace service 106 when a user enters text into a data field, selects a configuration, uploads an image, etc. Alternatively, the listing data access module 202 may access the listing data from a database, such as the online marketplace service 106 and / or a database of the data store 212. In any case, the listing data access module 202 may provide the listing data directly to other modules of the display conversion estimation and optimization system 108 and / or store the listing data in the data store 212, where the other modules of the display conversion estimation and optimization system 108 may access the data store 212.

[0048] The likelihood value determination module 204 uses the collected listing data to generate a likelihood value indicating the estimated likelihood that the new display will result in a conversion. A conversion can be any desired or specified result, such as selling the listed item, sharing the display, a predetermined number of users viewing the display, etc. The likelihood value determination module 204 uses a set of machine learning models that have been trained based on historical listing data to determine the likelihood value. The historical listing data includes data associated with previous displays posted to the online market. For example, the historical listing data includes listing data included in the previous display, such as a listing title, a listing description, an item image, a price, a shipping option (e.g., free shipping, paid shipping, etc.), a return option (e.g., free return, paid return, etc.), a feature (e.g., a structured name value selected to describe the item), etc. The historical listing data may also include performance data describing the interaction with the display, such as whether the display results in a conversion (e.g., selling the listed item), the number of days the display was active before the conversion, the number of times the display was viewed, the number of unique users who viewed the display, the number of likes received by the display, etc. The historical listing data may also include historical demand and / or supply data associated with previous displays, such as the number of other active displays posted at the same time for the same item, the number of user searches performed for the item while the display was active, and the like.

[0049] The likelihood value determination module 204 may use any type or combination of types of machine learning models to calculate the likelihood value of the new display. For example, the likelihood value determination module 204 may use a neural network, a linear regression, a classification model, etc. The resulting set of machine learning models outputs a likelihood value based on a set of input data. Therefore, the likelihood value determination module 204 collects input data and provides it as input to one or more machine learning models to generate a likelihood value. For example, the input data may include listing data for the new display and current demand and / or supply data, such as the number of other active displays of the item, the price associated with the other active displays, the number of searches for the item, etc.

[0050] The obtained likelihood value is a single value indicating the likelihood that the display will lead to conversion within a given time period (e.g., 1 day, 1 week, 2 weeks, etc.). In some embodiments, the likelihood value is determined based on a plurality of sub-values. For example, the likelihood value can be determined based on a sub-value calculated based only on the list data and another sub-value calculated based only on the demand and / or supply data. These sub-values ​​can each represent the likelihood that the display will lead to conversion based on a given input for calculating each sub-value. For example, a sub-value determined based on the list data can indicate the likelihood that the display will lead to conversion based only on the list data. As another example, a sub-value determined based on demand and / or supply data can indicate the likelihood that the display will lead to conversion based only on the current demand and / or supply of the item. Then, the likelihood value determination module 204 can determine the final likelihood value based on each of the sub-values, for example, by calculating an average, applying various weights, using the sub-value as an input to another trained machine learning model, etc.

[0051] These are just some examples of how likelihood value determination module 204 can calculate likelihood values ​​and are not meant to be limiting. Likelihood value determination module 204 can calculate likelihood values ​​using any of a variety of techniques, methods, machine learning models, and / or algorithms, and the present disclosure contemplates all such implementations.

[0052] As previously described, the likelihood value determination module 204 may continue to update the likelihood value as the user generating the new display inputs updated listing data. That is, the likelihood value determination module 204 may repeat the above process with updated listing data, demand data, and / or supply data at specified time intervals and / or when the user modifies the display. Figure 3 The functionality of the likelihood value determination module 204 is discussed in more detail.

[0053] The graphic indicator generation module 206 generates a graphic indicator representing a probability value. A graphic indicator is a graphical representation of a probability value, such as a graphic dial or meter indicating that an exhibition will lead to the probability of conversion. The graphic indicator provides a representation of the probability value that is easy and quick to read by the user. That is, the graphic indicator graphically represents to the user the probability that the exhibition will lead to conversion. To accomplish this, the graphic indicator may include a dial or meter representing the probability value, and different colors, icons, or other indicators to graphically represent the probability that the exhibition will lead to conversion. The pointer of the dial or meter may be positioned to indicate the probability value. In addition, the graphic indicator may use a color such as green to indicate that the exhibition has a high probability of leading to conversion, and may use a color such as red to indicate that the exhibition has a low probability of leading to conversion, and vice versa. As another example, the graphic indicator may include an icon or animation such as flame to indicate that the exhibition has a high probability of leading to conversion.

[0054] These are just a few examples of the types of graphical indicators that can be generated by the graphical indicator generation module 206 to represent the likelihood values, and are not meant to be limiting. The graphical indicator generation module 206 can generate any of a variety of graphical representations of values, such as graphs, charts, dials, meters, heat maps, etc., and the present disclosure contemplates all such embodiments. For example, in some embodiments, a graphical indicator can represent the likelihood values ​​over multiple time periods. That is, a graphical indicator can represent multiple likelihood values, each of which represents the likelihood that a display will result in a conversion within a different time period. For example, a graphical indicator can represent a first likelihood value that a display will result in a conversion within a week, a second likelihood value that a display will result in a conversion within two weeks, and a third likelihood value that a display will result in a conversion within three weeks. A graphical indicator can represent these multiple likelihood values ​​in a two-dimensional graph, wherein one axis represents the likelihood values ​​and the other axis represents time.

[0055] The suggestion generation module 208 generates suggested modifications for the display to increase the likelihood that the display will result in a conversion. The suggested modifications may be suggested changes to the listing data for the display, for example, by adding additional listing data, removing listing data, and / or modifying listing data. For example, the suggested modifications may be to increase the length of the item description, reduce the sale price, offer free shipping and / or free returns, upload more images, replace existing images with higher quality images, select features, etc.

[0056] The suggestion generation module 208 may use a machine learning model to generate suggested modifications. For example, a machine learning model used to generate a likelihood score may also output data indicating the negative or positive impact of various model features on the likelihood score. The machine learning model may generate a likelihood score based on various model features, such as item description length, price, image quality, characteristics, etc. The machine learning model may provide data indicating the impact of each feature on the resulting likelihood value, which the suggestion generation module 208 may use to determine suggested modifications to the display. The suggestion generation module 208 may identify the model features that have the greatest negative impact on the likelihood value and generate suggested modifications to improve those specified features. For example, given an output that the model feature of description length has a negative impact on the likelihood value, the suggestion generation module 208 may generate a suggested modification of not creating an item description length. As another example, given an output that the model feature of image quality has a negative impact on the likelihood value, the suggestion generation module 208 may generate a suggested modification of replacing the image with a higher quality image. As another example, given an output that the model feature of price has a negative impact on the likelihood value, the suggestion generation module 208 may generate a suggested modification of reducing the display price.

[0057] The suggestion generation module 208 can generate the suggested modifications based on the model features that have the greatest negative impact on the likelihood value. The suggestion generation module 208 can also calculate an estimated impact of performing the suggested modification, which can be included in the suggested modification. For example, the estimated impact can indicate an estimated increase in the likelihood value and / or updated likelihood value resulting from performing the suggested modification.

[0058] The output module 210 causes the graphical indicators and suggested modifications to be presented to the seller who is generating the new display. For example, the output module 210 provides data to the online service 106 and / or the client device 102 to cause the graphical indicators and suggested modifications to be presented to the seller. The graphical indicators and suggested modifications can be presented in the display interface that the seller is using to generate the new display.

[0059] Figure 3 2 is a block diagram of the likelihood value determination module 204 according to some example embodiments. In order to avoid obscuring the subject matter of the present invention with unnecessary detail, Figure 3 Various functional components (e.g., modules) that are not relevant to conveying an understanding of the subject matter of the present invention have been omitted. However, a skilled person will readily recognize that various additional functional components may be supported by likelihood value determination module 204 to facilitate additional functions not specifically described herein. In addition, Figure 2 The various functional modules depicted in the may reside on a single computing device, or may be distributed across several computing devices in various arrangements, such as those used in a cloud-based architecture.

[0060] As shown in the figure, the likelihood value determination module 204 includes a data collection module 302 , a machine learning model generation module 304 , and a likelihood value generator 306 .

[0061] The data collection module 302 collects data for generating (e.g., training) a set of machine learning models that output likelihood values, and collects data used as input to the generated set of machine learning models to generate likelihood values. For example, the data collection module 302 collects historical list data, which is used to train the machine learning model. The historical list data includes data associated with previous displays posted to the online market. For example, the historical list data includes list data included in the previous display, such as the list title, list description, item image, price, shipping options (e.g., free shipping, paid shipping, etc.), return options (e.g., free return, paid return, etc.), features, etc. The historical list data may also include performance data describing the interaction with the list, such as whether the list leads to a conversion (e.g., selling the listed item), the number of days the list was active before the conversion, the number of times the list was viewed, the number of unique users who viewed the list, the number of likes the list received, etc. The historical list data may also include historical demand and / or supply data associated with the previous display, such as the number of other active displays posted at the same time for the same item, the number of user searches, the number of times the user searched for the item when the list was active, etc.

[0062] The data collection module 302 can access the historical list data from the online service 106 and / or the data store 212. For example, the data collection module 302 can communicate with the online service 106 to request the historical list data. Alternatively, the online service 106 can automatically transmit the historical list data to the display conversion estimation and optimization system 108 at regular intervals. In an embodiment where the display conversion estimation and optimization system 108 is integrated into the online service 106, the historical list data can be stored in the data store 212. Therefore, the data collection module 302 can access the historical list data from the data store 212.

[0063] The data collection module 302 also collects current list data for generating the likelihood value of the display. For example, the current list data may include list data entered by the user while the user is in the process of generating a new display. The current list data may also include current supply and / or demand data, such as the number of active displays of the same or similar items, the number of search requests for the same or similar items, list data of active displays of the same or similar items, etc. The data collection module 302 may similarly collect current list data from the online service 106 and / or the data store 212. The data collection module 302 may provide the collected data to other modules of the likelihood value determination module 204 and / or store the collected data in the data store 212, where the data store 212 is accessible to the other modules.

[0064] The machine learning model generation module 304 generates a set of machine learning models based on the historical list data. The trained set of machine learning models outputs a probability value based on a set of input data. The probability value indicates the estimated probability that the display will lead to a conversion within a given time period, such as within a week, two weeks, a month, etc.

[0065] The machine learning model generation module 304 can generate any of various types of machine learning models and or combinations of models. For example, the machine learning model generation module 304 can generate separate machine learning models based on different subsets of historical list data. Each of these machine learning models can output sub-values ​​based on different sets of input data. For example, a machine learning model trained only based on the list data included in the historical display can output a sub-value indicating the likelihood that the display will result in a conversion based only on the list data included in the new display. As another example, a machine learning model trained only based on the supply and / or demand for similar items can output a sub-value indicating the likelihood that the display will result in a conversion based only on the current supply and / or demand for the item.

[0066] The machine learning model generation module 304 can train another machine learning model that outputs a final likelihood value based on a plurality of sub-values. For example, the machine learning model will receive as input a plurality of sub-values ​​representing the likelihood that the listing will result in a conversion based on some subset of the data, such as the listing data, the demand data, or the supply data, and output a final likelihood value indicating the overall likelihood that the listing will result in a conversion.

[0067] The likelihood value generator 306 uses the generated set of machine learning models to generate the likelihood value of the display. For example, the likelihood value generator 306 uses the data collected by the data collection module 302 as input to a set of machine learning models, which output the likelihood value of the list.

[0068] 4A to 4H An example of a display interface 400 providing display conversion estimation and optimization according to some example embodiments is shown. Figure 4AAs shown, the display interface 400 allows a user to enter listing data to generate a new display to be published to the online market. For example, the display interface includes a title input field 402, a price input field 404, an image input field 406, an item description input field 408, a shipping configuration field 410, a return configuration field 412, and a feature selection field 414. A user can use the display interface to provide listing data to generate a new display. For example, a user can use the title input field 402 to enter a listing title for the new display, use the price input field 404 to enter a price for the listing, use the image input field 406 to provide an image of the display, use the item description field 408 to enter an item description for the listing, use the shipping configuration field 410 to configure whether shipping will be included in the sales price, use the return configuration field 412 to configure whether returns will be free or paid, and use the feature selection field to select one or more feature tags that describe the listed items.

[0069] The feature tags may be structured name values ​​that may be selected by a user to describe and / or categorize items provided by the display. For example, a user may select from multiple sets of feature tags in different categories to describe the listed items, e.g., by selecting from a set of feature tags that identify compatible brands, included features, item types, item conditions, etc. The selected feature tags may be used to provide search results to search queries entered by users of the online marketplace. Thus, the inclusion of feature tags in the display may result in an increase in the number of search results in which the listing appears, as well as an increase in the positioning of the listing in the search results. Thus, a greater number of interested users may see the listing, resulting in a corresponding increase in the likelihood that the display will result in a conversion.

[0070] The display interface 400 also includes a publish display button 420 that enables a user to publish a listing to the online marketplace based on the listing data provided in the various fields of the display interface 400. For example, a user who has completed entering listing data may simply initiate (e.g., click) the publish display button 420 to cause the new display to be published to the online marketplace.

[0071] The display interface 400 also includes a graphical indicator 416 that provides a graphical representation of how likely the display is to result in a conversion based on the listing data entered into the fields of the display interface 400. For example, the graphical indicator 416 represents a likelihood value calculated based on the listing data entered into the fields of the display interface 400. The likelihood value represents an estimated likelihood that the display will result in a conversion within a given time frame, such as one week, two weeks, etc. As shown, the graphical indicator is a graphical representation of a dial that includes a pointer positioned within the dial to indicate the likelihood value. A numerical representation 418 of the likelihood value is presented next to the graphical indicator 416. A user can use the graphical indicator 416 and / or the numerical representation 418 to quickly and easily determine the likelihood that the display will result in a conversion given the listing data that has been entered. As shown, listing data has not yet been entered into the display interface 400. Figure 4A 4. Thus, graphical indicator 416 and numerical representation 418 indicate that there is a 0% chance that the display will result in a conversion.

[0072] Figure 4B shows that as the user enters the list data into Figure 4A As shown, the user has entered the listing title "Used Snorkels" into title input field 402 and a price of $50 into price input field 404. As a result of adding the listing data, the likelihood that the listing will result in a conversion has increased from $40 to $50. Figure 4A The display interface 400 shown increases. This is indicated by a change in the position of the pointer shown in the graphical indicator 416 and a change in the numerical representation 418, which indicates that the display has a 12% likelihood of resulting in a conversion if published based on the input listing data (e.g., listing title and display price). A user who is satisfied with the likelihood that the display will result in a conversion can choose to publish the display by activating the publish display button 420. Alternatively, a user who is dissatisfied with the likelihood that the display will result in a conversion (e.g., the user prefers a higher likelihood value) can use the display interface 400 to update the display by adding additional listing data, modifying existing listing data, and / or deleting listing data.

[0073] Figure 4C Shows that the user has modified the list by adding additional list data Figure 4B 4. As shown, the user has added "Image 1" to the image input field 406. This may include an image file that the user has uploaded for inclusion in the display, such as an image of an item offered for sale by the display. As a result of adding the listing data (e.g., Image 1), the likelihood that the display will result in a conversion has increased from 1. Figure 4BThe display interface 400 shown increases. This is indicated by a change in the position of the pointer shown in the graphical indicator 416 and a change in the numerical representation 418, which indicates that the display has a 25% likelihood of resulting in a conversion if published based on the input listing data (e.g., listing title, display price, and listing image). A user who is satisfied with the likelihood that the display will result in a conversion can choose to publish the display by activating the publish display button 420. Alternatively, a user who is dissatisfied with the likelihood that the display will result in a conversion (e.g., the user prefers a higher likelihood value) can use the display interface 400 to update the display by adding additional listing data, modifying existing listing data, and / or deleting listing data.

[0074] Figure 4D Shows that the user has modified the list by adding additional list data Figure 4C 4. As shown, the user has added an item description to the item description field 408. The item description may include text describing the item offered for sale by the listing. As a result of adding listing data (e.g., item description), the likelihood that the listing will result in a conversion has increased from Figure 4C The display interface 400 shown increases. This is indicated by a change in the position of the pointer shown in the graphical indicator 416 and a change in the numerical representation 418, which indicates that the display now has a 41% likelihood of resulting in a conversion if published based on the input listing data (e.g., listing title, display price, listing image, and listing description). A user who is satisfied with the likelihood that the display will result in a conversion can choose to publish the display by activating the publish display button 420. Alternatively, a user who is dissatisfied with the likelihood that the display will result in a conversion (e.g., the user prefers a higher likelihood value) can use the display interface 400 to update the display by adding additional listing data, modifying existing listing data, and / or deleting listing data.

[0075] As previously mentioned, some users may be unsure how to increase the likelihood that their display will result in a conversion. For example, the user may be unsure what changes to make to the listing data, what listing data to add, etc. As shown, the display interface 400 includes suggested modifications 422 that provide guidance to the user on increasing the likelihood that the display will result in a conversion. For example, the suggested modifications 422 are text messages notifying the user that adding free shipping will increase the likelihood that the display will result in a conversion. The user can implement the suggested modifications to increase the likelihood that the display will result in a conversion.

[0076] Figure 4E shows that since the user modified the Figure 4D4. As shown, the user has updated the shipping configuration field 410 to indicate that free shipping is included in the display. As a result of this update, the likelihood that the display will result in a conversion has changed from Figure 4D The display interface 400 shown increases. This is indicated by a change in the position of the pointer shown in the graphical indicator 416 and a change in the numerical representation 418, which indicates that the display has a 50% likelihood of resulting in a conversion if published based on the input listing data (e.g., listing title, display price, listing image, item description, and shipping configuration). A user who is satisfied with the likelihood that the display will result in a conversion can choose to publish the display by activating the publish display button 420. Alternatively, a user who is dissatisfied with the likelihood that the display will result in a conversion (e.g., the user prefers a higher likelihood value) can use the display interface 400 to update the display by adding additional listing data, modifying existing listing data, and / or deleting listing data.

[0077] As shown, the display interface 400 includes another suggested modification 422 that provides guidance to the user on increasing the likelihood that the display will result in a conversion. The suggested modification 422 informs the user that adding free returns will increase the likelihood that the display will result in a conversion. Figure 4D The proposed modifications presented in 422 are different, Figure 4E The suggested modification 422 in indicates the estimated impact of implementing the modification. For example, the suggested modification 402 indicates that implementing the modification will increase the likelihood that the display will result in a conversion by an additional 12%. The user can use the estimated impact to determine whether to implement the modification (e.g., determine whether it is worth offering free returns to increase the likelihood that the display will result in a conversion by 12%).

[0078] Figure 4F shows that the user modified the order by indicating that free returns are provided (e.g., the buyer will not be charged for returning the item). Figure 4E As shown, the user has updated the return configuration field 412 to indicate that free returns are included in the display. As a result of this update, the likelihood that the display will result in a conversion has changed from Figure 4EThe display interface 400 shown increases. This is indicated by a change in the position of the pointer shown in the graphical indicator 416 and a change in the numerical representation 418, which indicates that the display has a 62% likelihood of resulting in a conversion if published based on the input listing data (e.g., listing title, display price, listing image, item description, shipping configuration, and return configuration). A user who is satisfied with the likelihood that the display will result in a conversion can choose to publish the display by activating the publish display button 420. Alternatively, a user who is dissatisfied with the likelihood that the display will result in a conversion (e.g., the user prefers a higher likelihood value) can use the display interface 400 to update the display by adding additional listing data, modifying existing listing data, and / or deleting listing data.

[0079] As shown, the display interface 400 includes another suggested modification 422, which provides guidance to the user on increasing the likelihood that the display will lead to conversions. The suggested modification 422 informs the user that adding features, images, and longer descriptions of the items will increase the likelihood that the display will lead to conversions. The user can choose to implement one, two, or none of the suggested modifications.

[0080] Figure 4G Shows that the user has modified the list by adding additional list data Figure 4F The display interface 400 shown in the figure is obtained by the user. As shown, the user has updated the image input field 406 to add two additional images (e.g., Image 2 and Image 3), the item description input field 408 to lengthen the item description, and the feature data field 414 to add two feature tags (Full Mask, Deflation Valve).

[0081] As previously described, the characteristic tags can be selected from a predetermined set of characteristic tags associated with the item. For example, the online market service 106 can maintain characteristic tags for various item types. Therefore, when a user is generating a display for a particular item, the online market service 106 can collect characteristic tags corresponding to the item, which can be presented and selected within the display interface 400. For example, each characteristic tag can indicate a possible classification of the item by describing a subset type of item, features provided by a specific item, compatible products, etc. The user generating the display can select from the presented characteristic tags based on the listed items. That is, the user can select the presented characteristic tags that appropriately classify the listed items.

[0082] As shown, the feature tags added to the feature selection field 414 include the feature tags Full Cover and Deflate Valve. The feature tag Full Cover describes a subset type of item by indicating that the listed second-hand snorkel is a Full Cover snorkel. The user may have selected the feature tag Full Cover from a set of presented feature tags, which include other types of snorkels, such as classic snorkels, dry snorkels, or flexible snorkels. The feature tag Deflate Valve describes the features provided by the listed second-hand snorkel. That is, the feature tag indicates that the second-hand snorkel includes a deflate valve.

[0083] The selected characteristic tags are used to provide search results to users of the online marketplace and can increase the likelihood that the listing results in a set of search results and / or the location of the search results. Thus, the listing is more likely to be presented to an interested user, which also increases the likelihood that the listing results in a conversion. For example, the listing is more likely to be presented in response to a user search query such as "used full face snorkel with purge valve".

[0084] As a result of these updates, the likelihood that a display will result in a conversion has gone from Figure 4G The display interface 400 shown increases. This is indicated by a change in the position of the pointer shown in the graphical indicator 416 and a change in the numerical representation 418, which indicates that the display has a 75% likelihood of resulting in a conversion if published based on the input listing data (e.g., listing title, display price, listing image, item description, and shipping configuration). A user who is satisfied with the likelihood that the display will result in a conversion can choose to publish the display by activating the publish display button 420. Alternatively, a user who is dissatisfied with the likelihood that the display will result in a conversion (e.g., the user prefers a higher likelihood value) can use the display interface 400 to update the display by adding additional listing data, modifying existing listing data, and / or deleting listing data.

[0085] As shown, the display interface 400 includes another suggested modification 422 that provides guidance to the user on increasing the likelihood that the display will result in a conversion. The suggested modification 422 informs the user that reducing the display price to $40 will increase the likelihood that the display will result in a conversion within the next week to 95%. The user can use the estimated impact to determine whether to implement the modification (e.g., determine whether it is worth reducing the cost to $40 to increase the likelihood that the display will result in a conversion by 20%).

[0086] Figure 4H Shows that the user modifies the previous display data Figure 4G The display interface 400 shown in FIG. 4 shows that the user has updated the display price field 404 to reduce the display price to $40. As a result of this update, the probability that the display will result in a conversion has changed from $40 to $50. Figure 4G The display interface 400 shown increases. This is indicated by a change in the position of the pointer shown in the graphical indicator 416 and a change in the numerical representation 418, which indicates that the display has a 95% likelihood of resulting in a conversion if published based on the input listing data (e.g., listing title, display price, listing image, item description, and shipping configuration). A user who is satisfied with the likelihood that the display will result in a conversion can choose to publish the display by activating the publish display button 420. Alternatively, a user who is dissatisfied with the likelihood that the display will result in a conversion (e.g., the user prefers a higher likelihood value) can use the display interface 400 to update the display by adding additional listing data, modifying existing listing data, and / or deleting listing data.

[0087] As shown, the display interface 400 includes another suggested modification 422 that does not include a suggested change to the listing data, but rather informs the user of the likelihood of the display leading to a conversion based on different time periods. For example, the suggested modification 422 informs the user that the display has a 95% likelihood of leading to a conversion within the next week and a 98% likelihood of leading to a conversion within the next two weeks.

[0088] Figure 5 is a flow chart illustrating a method 500 for providing display conversion estimates according to some example implementations. The method 500 may be implemented in computer-readable instructions that are executed by one or more processors, such that the operations of the method 500 may be performed in part or in whole by the display conversion and estimation system 108; therefore, the method 500 is described below by way of example and by reference. However, it should be understood that at least some of the operations of the method 500 may be deployed on various other hardware configurations, and the method 500 is not intended to be limited to the display conversion and estimation system 108.

[0089] At operation 502, the list data access module 202 accesses an initial set of list data to generate a display. The list data may be list data entered by a user in the process of generating a new display. For example, the user may enter the list data into a data field of a display interface. The list data access module 202 may access the list data from an online service 106 that facilitates the display interface and / or from a data store 212 that stores the list data.

[0090] At operation 504, the likelihood value determination module 204 determines a likelihood value based on the initial set of listing data. The likelihood value indicates the likelihood that the display will result in a conversion within a given time period based on the initial set of listing data provided by the user. For example, the likelihood value determination module 204 can use the initial set of listing data as input into a set of machine learning models trained based on historical listing data. The set of machine learning models outputs a likelihood value based on the given input.

[0091] At operation 506, the output module 210 causes a graphical indicator representing the likelihood value to be presented. The graphical indicator is a graphical representation of the likelihood value, such as a graphical dial or meter. For example, the graphical dial may include a pointer positioned to represent the likelihood value. The graphical indicator may be generated by the graphical indicator generation module 206 and provided to the output module 210, which causes the graphical indicator to be presented to the user generating the display. For example, the output module 210 provides data to the online service 106 and / or the client device 102 so that the graphical indicator is presented in the display interface being used by the user to generate a new display. The graphical indicator presented quickly informs the user of the likelihood that the display will result in a conversion based on the provided list data. The user may use this information to determine whether to publish the display as is or to continue to modify the display to increase the likelihood that the display will result in a conversion.

[0092] The display conversion estimation and optimization system 108 can update the graphical indicator in real time or near real time. Therefore, at operation 508, the list data access module 202 accesses the list data of the updated set to generate the display. The list data of the updated set can include additional list data provided by the user, modifications to the list data of the initial set, and / or removal of list data.

[0093] At operation 510, the likelihood value determination module 204 determines an updated likelihood value based on the list data of the update group. The updated likelihood value indicates the likelihood of an update resulting from a display of the list data being updated by a user leading to a conversion.

[0094] At operation 512, the output module 210 updates the presentation of the graphical indicator based on the updated likelihood value. Thus, the user is presented with a likelihood value that reflects the likelihood that the listing will result in a conversion when the user performs an update to the listing.

[0095] Figure 66 is a flow chart illustrating a method 600 for providing display conversion optimization according to some example implementations. The method 600 may be implemented in computer-readable instructions that are executed by one or more processors such that the operations of the method 600 may be performed in part or in whole by the display conversion and estimation system 108; therefore, the method 600 is described below by way of example and by reference. However, it should be understood that at least some of the operations of the method 600 may be deployed on various other hardware configurations, and the method 600 is not intended to be limited to the display conversion and estimation system 108.

[0096] At operation 602, the suggestion generation module 208 determines a set of potential modifications to the new display. The set of potential modifications can be a predetermined set of modifications that can be made to the display, such as modifying certain listing data, adding certain listing data, removing certain listing data, etc. The set of potential modifications can be related to a set of model features used to generate a likelihood score for the display. For example, a machine learning model can generate a likelihood score based on various model features such as item description length, price, image quality, etc. Each potential modification can be bound to one of the model features to cause a change in the feature provided to the machine learning model when generating a likelihood value.

[0097] At operation 604, the suggestion generation module 208 determines the impact of each suggested modification as the likelihood that the display will result in a conversion. The machine learning model used to generate the likelihood score may also output data indicating the negative impact or positive impact of various model features on the likelihood score. The suggestion generation module 208 may use this data to determine the positive impact of each suggested modification on the likelihood value. For example, the suggestion generation module 208 may identify the model features that have the greatest negative impact on the likelihood value and / or have the greatest negative variance from the average or maximum positive impact of the model features. The suggestion generation module 208 may identify potential positive impacts based on variance. For example, the impact of a suggested modification may be based on the variance between the current impact of the model feature and the average or maximum positive impact of the model feature.

[0098] At operation 606, the suggestion generation module 208 selects a suggested modification based on the impact of the suggested modification on the likelihood that the display will result in a conversion. For example, the suggestion generation module 208 may select the suggested modification determined to have the highest positive impact.

[0099] At operation 608, the output module 210 causes the suggested modifications to be presented. For example, the output module 210 provides data to the online service 106 and / or the client device 102 so that text describing the suggested modifications is presented within a display interface being used by the user to generate a new display. The suggested modifications inform the user of modifications that the user can make to the display to increase the likelihood that the display will result in a conversion.

[0100] Software Architecture

[0101] Figure 7 is a block diagram illustrating an example software architecture 706 that may be used in conjunction with the various hardware architectures described herein. Figure 7 is a non-limiting example of software architecture 706 and it will be appreciated that many other architectures may be implemented to facilitate the functionality described herein. Software architecture 706 may be implemented in a variety of applications such as Figure 8 800, which includes a processor 804, a memory 814, and (input / output) (I / O) components 818, among others. A representative hardware layer 752 is shown and may represent, for example, Figure 8 The machine 800 of the embodiment of the present invention. The representative hardware layer 752 includes a processing unit 754 having associated executable instructions 704. The executable instructions 704 represent executable instructions of the software architecture 706, including implementations of the methods, components, etc. described herein. The hardware layer 752 also includes a memory and / or storage module 756 also having executable instructions 704. The hardware layer 752 may also include other hardware 758.

[0102] exist Figure 7 In the example architecture of , software architecture 706 can be conceptualized as a stack of layers, each of which provides specific functionality. For example, software architecture 706 may include layers such as operating system 702, library 720, framework / middleware 718, application 716, and presentation layer 714. In operation, application 716 and / or other components within the layer may call application programming interface (API) call 708 through the software stack and receive responses such as message 712 in response to API call 708. The layers shown are representative in nature, and not all software architectures have all layers. For example, some mobile or dedicated operating systems may not provide framework / middleware 718, while other operating systems may provide such layers. Other software architectures may include additional layers or different layers.

[0103] The operating system 702 can manage hardware resources and provide public services. The operating system 702 can include, for example, a kernel 722, services 724, and drivers 726. The kernel 722 can be used as an abstraction layer between the hardware and other software layers. For example, the kernel 722 can be responsible for memory management, processor management (e.g., scheduling), component management, networking, security settings, etc. The services 724 can provide other public services for other software layers. The driver 726 is responsible for controlling the underlying hardware or interfacing with the underlying hardware. For example, depending on the hardware configuration, the driver 726 includes a display driver, a camera driver, drives, flash drives, serial communications drivers (e.g., Universal Serial Bus (USB) drivers), Drivers, audio drivers, power management drivers, etc.

[0104] The library 720 provides a common infrastructure used by the application 716 and / or other components and / or layers. The library 720 provides functions that allow other software components to perform tasks in an easier way than directly interfacing with the underlying operating system 702 functions (e.g., kernel 722, service 724, and / or driver 726). The library 720 may include a system library 744 (e.g., C standard library), which may provide functions such as memory allocation functions, string manipulation functions, mathematical functions, etc. In addition, the library 720 may include an API library 746 such as a media library (e.g., a library that supports the presentation and manipulation of various media formats such as MPEG4, H.264, MP3, AAC, AMR, JPG, PNG), a graphics library (e.g., an OpenGL framework that can be used to present 2D and 3D graphics content on a display), a database library (e.g., SQLite that can provide various relational database functions), a network library (e.g., WebKit that can provide network browsing functions), etc. The library 720 may also include a variety of other libraries 748 to provide many other APIs to the application 716 and other software components / modules.

[0105] Framework / middleware 718 (also sometimes referred to as middleware) provides a higher-level common infrastructure that can be used by applications 716 and / or other software components / modules. For example, framework / middleware 718 can provide various graphical user interface (GUI) functions, advanced resource management, advanced location services, etc. Framework / middleware 718 can provide a wide range of other APIs that can be used by applications 716 and / or other software components / modules, some of which can be specific to a particular operating system 702 or platform.

[0106] Applications 716 include built-in applications 738 and / or third-party applications 740. Examples of representative built-in applications 738 may include, but are not limited to, contact applications, browser applications, book reader applications, location applications, media applications, messaging applications, and / or game applications. Third-party applications 740 may include applications that are run by entities other than the vendor of a particular platform using ANDROID TM or IOS TM Software Development Kit (SDK) for developing applications and can be used on platforms such as IOS TM ANDROID TM , Mobile software running on the mobile operating system of the phone or other mobile operating systems. The third-party application 740 can call API calls 708 provided by the mobile operating system (eg, operating system 702) to facilitate the functions described herein.

[0107] Applications 716 may create a UI using built-in operating system functionality (e.g., kernel 722, services 724, and / or drivers 726), libraries 720, and framework / middleware 718 to interact with a user of the system. Alternatively or additionally, in some systems, interaction with the user may occur through a presentation layer such as presentation layer 714. In these systems, the application / component "logic" may be separated from the characteristics of the application / component that interact with the user.

[0108] Figure 8 is a block diagram illustrating components of a machine 800 that is capable of reading instructions 704 from a machine-readable medium (e.g., a machine-readable storage medium) and performing any one or more of the methods discussed herein, according to some example embodiments. Specifically, Figure 8 A graphical representation of a machine 800 in the form of an example of a computer system is shown, within which instructions 810 (e.g., software, programs, applications, small applications, apps or other executable codes) for causing the machine 800 to perform any one or more of the methods discussed herein can be executed. Therefore, instructions 810 can be used to implement the modules or components described herein. Instructions 810 convert a general unprogrammed machine 800 into a programmed specific machine 800, thereby performing the described and illustrated functions in the described manner. In an alternative embodiment, the machine 800 operates as an independent device or can be coupled (e.g., networked) to other machines. In a networked deployment, the machine 800 can operate as a server machine or a client machine in a server-client network environment, or operate as a peer machine in a peer-to-peer (or distributed) network environment. The machine 800 may include, but is not limited to, a server computer, a client computer, a PC, a tablet computer, a laptop computer, a netbook, a set-top box (STB), a personal digital assistant (PDA), an entertainment media system, a cellular phone, a smart phone, a mobile device, a wearable device (e.g., a smart watch), a smart home device (e.g., a smart home appliance), other smart devices, network appliances, a network router, a network switch, a network bridge, or any machine 800 capable of executing instructions 810 that specify actions to be taken by the machine 800, either sequentially or otherwise. In addition, while only a single machine 800 is shown, the term "machine" should also be taken to include a collection of machines that individually or jointly execute instructions 810 to perform any one or more of the methodologies discussed herein.

[0109] The machine 800 may include a processor 804, a memory / storage 806, and an I / O component 818 that may be configured to communicate with each other, for example, via a bus 802. The memory / storage 806 may include a memory 814, such as a main memory or other memory storage, and a storage unit 816, both of which are accessible by the processor 804, such as via the bus 802. The storage unit 816 and the memory 814 store instructions 810 that implement any one or more of the methods or functions described herein. The instructions 810 may also reside, in whole or in part, within the memory 814, within the storage unit 816, within at least one processor 804 (e.g., within a cache memory of a processor), or within any suitable combination thereof during execution thereof by the machine 800. Thus, the memory 814, the storage unit 816, and the memory of the processor 804 are examples of machine-readable media.

[0110] The I / O components 818 may include a variety of components that receive input, provide output, generate output, transmit information, exchange information, capture measurements, etc. The specific I / O components 818 included in a particular machine 800 will depend on the type of machine. For example, a portable machine such as a mobile phone will likely include a touch input device or other such input mechanism, while a headless server machine will likely not include such a touch input device. It will be appreciated that the I / O components 818 may include Figure 8 828. The I / O components 818 are grouped according to function only for the purpose of simplifying the following discussion, and the grouping is by no means limiting. In various example embodiments, the I / O components 818 may include output components 826 and input components 828. The output components 826 may include visual components (e.g., displays such as plasma display panels (PDPs), light emitting diode (LED) displays, liquid crystal displays (LCDs), projectors, or cathode ray tubes (CRTs)), acoustic components (e.g., speakers), tactile components (e.g., vibration motors, resistance mechanisms), other signal generators, etc. The input components 828 may include alphanumeric input components (e.g., keyboards, touch screens configured to receive alphanumeric input, optical keyboards, or other alphanumeric input components), point-based input components (e.g., mice, touch pads, trackballs, joysticks, motion sensors, or other pointing instruments), tactile input components (e.g., physical buttons, touch screens or other tactile input components that provide location and force of touch or touch gestures), audio input components (e.g., microphones), etc.

[0111] In other example embodiments, the I / O component 818 may include a biometric component 830, a motion component 834, an environmental component 836, or a position component 838, among a wide range of other components. For example, the biometric component 830 may include a component for detecting expressions (e.g., hand expressions, facial expressions, voice expressions, body postures, or eye tracking), measuring biosignals (e.g., blood pressure, heart rate, body temperature, sweat, or brain waves), identifying a person (e.g., voice recognition, retinal recognition, facial recognition, fingerprint recognition, or EEG-based recognition), etc. The motion component 834 may include an acceleration sensor component (e.g., an accelerometer), a gravity sensor component, a rotation sensor component (e.g., a gyroscope), etc. The environment component 836 may include, for example, an illumination sensor component (e.g., a photometer), a temperature sensor component (e.g., one or more thermometers that detect ambient temperature), a humidity sensor component, a pressure sensor component (e.g., a barometer), an acoustic sensor component (e.g., one or more microphones that detect background noise), a proximity sensor component (e.g., an infrared sensor that detects nearby objects), a gas sensor (e.g., a gas detection sensor that detects the concentration of dangerous gases to ensure safety or for measuring pollutants in the atmosphere), or other components that can provide indications, measurements, or signals corresponding to the surrounding physical environment. The location component 838 may include a positioning sensor component (e.g., a GPS receiver component), an altitude sensor component (e.g., an altimeter or barometer that detects air pressure, from which the altitude can be obtained), an orientation sensor component (e.g., a magnetometer), etc.

[0112] A variety of technologies may be used to achieve communication. The I / O components 818 may include a communication component 840 that is operable to couple the machine 800 to the network 832 or the device 820 via coupling 824 and coupling 822, respectively. For example, the communication component 840 may include a network interface component or other suitable device to interface with the network 832. In other examples, the communication component 840 may include a wired communication component, a wireless communication component, a cellular communication component, a near field communication (NFC) component, Parts (e.g. Low energy consumption), Components and other communication components that provide communication via other forms. Device 820 can be another machine or any of a variety of peripheral devices (e.g., a peripheral device coupled via USB).

[0113] In addition, the communication component 840 can detect an identifier or include a component operable to detect an identifier. For example, the communication component 840 can include a radio frequency identification (RFID) tag reader component, an NFC smart tag detection component, an optical reader component (e.g., an optical sensor for detecting one-dimensional barcodes such as universal product codes (UPC) barcodes, multi-dimensional barcodes such as quick response (QR) codes, Aztec codes, data matrix, data symbols (Dataglyph), MaxiCode, PDF417, Ultra Code, UCC RSS-2D barcodes and other optical codes) or an acoustic detection component (e.g., a microphone for identifying an audio signal of a tag). In addition, various information can be derived via the communication component 840, such as a location via an Internet Protocol (IP) geographic location, a location via Wi-Fi signal triangulation, a location via detection of an NFC beacon signal that can indicate a specific location, and the like.

[0114] Glossary

[0115] A "carrier wave signal" in this context refers to any intangible medium capable of storing, encoding, or carrying the instructions 810 to be executed by the machine 800 and includes a digital or analog communications signal or other intangible medium to facilitate communication of the instructions 810. The instructions 810 may be sent or received over the network 832 using a transmission medium via a network interface device and using any of a number of well-known transmission protocols.

[0116] A "client device" in this context refers to any machine 800 that interfaces with a communication network 832 to obtain resources from one or more server systems or other client devices. The client devices 102, 104 may be, but are not limited to, mobile phones, desktop computers, laptop computers, PDAs, smart phones, tablet computers, ultrabooks, netbooks, multiple laptop computers, multiprocessor systems, microprocessor-based or programmable consumer electronics, game consoles, STBs, or any other communication device that a user may use to access the network 832.

[0117] A "communication network" in this context refers to one or more portions of a network 832, which may be an ad hoc network, an intranet, an extranet, a virtual private network (VPN), a LAN, a wireless LAN (WLAN), a WAN, a wireless WAN (WWAN), a metropolitan area network (MAN), the Internet, a portion of the Internet, a portion of the public switched telephone network (PSTN), a plain old telephone service (POTS) network, a cellular telephone network, a wireless network, The network 832 or a portion of the network 832 may include a wireless network or a cellular network, and the coupling may be a code division multiple access (CDMA) connection, a global system for mobile communications (GSM) connection, or other type of cellular or wireless coupling. In this example, the coupling may implement any of various types of data transmission technologies, such as single carrier radio transmission technology (1xRTT), evolution data optimized (EVDO) technology, general packet radio service (GPRS) technology, enhanced data rates for GSM evolution (EDGE) technology, the third generation partnership project (3GPP) including 3G, the fourth generation wireless (4G) network, the universal mobile telecommunications system (UMTS), high speed packet access (HSPA), world wide interoperability for microwave access (WiMAX), long term evolution (LTE) standards, other standards defined by various standard setting organizations, other remote protocols, or other data transmission technologies.

[0118] "Machine-readable medium" in this context refers to a component, device, or other tangible medium capable of temporarily or permanently storing instructions 810 and data, and may include, but is not limited to, random access memory (RAM), read-only memory (ROM), buffer memory, flash memory, optical media, magnetic media, cache memory, other types of storage devices (e.g., erasable programmable read-only memory (EEPROM)), and / or any suitable combination thereof. The term "machine-readable medium" should be taken to include a single medium or multiple media (e.g., a centralized or distributed database or associated cache memory and server) capable of storing instructions 810. The term "machine-readable medium" should also be taken to include any medium or combination of multiple media capable of storing instructions 810 (e.g., code) executed by the machine 800, such that the instructions 810, when executed by one or more processors 804 of the machine 800, causes the machine 800 to perform any one or more of the methods described herein. Accordingly, "machine-readable medium" refers to a single storage device or device, as well as a "cloud-based" storage system or storage network including multiple storage devices or devices. The term "machine-readable medium" does not include the signal itself.

[0119] "Component" in this context refers to a device, physical entity or logic with boundaries defined by function or subroutine calls, branch points, APIs or other technologies provided for partitioning or modularizing specific processing or control functions. Components can be combined with other components via their interfaces to perform machine processing. Components can be part of a program that encapsulates functional hardware units designed for use with other components and generally performs specific functions of related functions. Components can constitute software components (e.g., codes implemented on machine-readable media) or hardware components. Hardware components are tangible units that can perform certain operations and can be configured or arranged in a certain physical manner. In various example embodiments, one or more computer systems (e.g., independent computer systems, client computer systems or server computer systems) or one or more hardware components of a computer system (e.g., a processor or processor group 804) can be configured to operate to perform certain operations as described herein by software (e.g., application 716 or application part). Hardware components can also be implemented mechanically, electronically or any suitable combination thereof. For example, a hardware component may include a dedicated circuit system or logic that is permanently configured to perform certain operations. The hardware component may be a dedicated processor, such as a field programmable gate array (FPGA) or an application specific integrated circuit (ASIC). The hardware component may also include a programmable logic or circuit system that is temporarily configured to perform certain operations by software. For example, the hardware component may include software executed by a general-purpose processor 804 or other programmable processor 804. Once configured by such software, the hardware component becomes a specific machine 800 (or a specific component of a machine 800), which is uniquely customized to perform the configured function and is no longer a general-purpose processor 804. It will be understood that the decision to implement the hardware component mechanically, in a dedicated and permanently configured circuit system, or in a temporarily configured circuit system (e.g., configured by software) can be driven by cost and time considerations. Therefore, the phrase "hardware component" ("hardware-implemented component") should be understood to include a tangible entity, that is, an entity that is physically constructed, permanently configured (e.g., hardwired) or temporarily configured (e.g., programmed) to operate in some way or perform certain operations described herein. Considering an embodiment in which the hardware component is temporarily configured (e.g., programmed), each of the hardware components does not need to be configured or instantiated at any time. For example, in the case where the hardware components include a general-purpose processor 804 that is configured by software to become a special-purpose processor, the general-purpose processor 804 can be configured into respectively different special-purpose processors (e.g., including different hardware components) at different times. The software accordingly configures the specific processor or processors 804 to, for example, constitute a specific hardware component at one time and constitute different hardware components at different times.Hardware components can provide information to other hardware components and receive information from other hardware components. Therefore, the described hardware components can be considered to be coupled in communication. In the case of multiple hardware components at the same time, communication can be achieved by signal transmission (for example, by appropriate circuits and bus 802) between or among two or more hardware components. In the embodiment in which multiple hardware components are configured or instantiated at different times, the communication between such hardware components can be achieved, for example, by storing information in a memory structure accessible to multiple hardware components and retrieving information in the memory structure. For example, a hardware component can perform an operation, and the output of the operation is stored in a memory device coupled in communication. Then, other hardware components can access the memory device at a subsequent time to retrieve and process the stored output. The hardware component can also initiate communication with an input or output device, and can operate on resources (for example, the collection of information). The various operations of the example method described herein can be performed at least in part by one or more processors 804 that are temporarily configured (for example, by software) or permanently configured to perform related operations. Whether it is a temporary configuration or a permanent configuration, such a processor 804 can constitute a processor-implemented component that operates to perform one or more operations or functions described herein. As used herein, "processor-implemented components" refer to hardware components implemented using one or more processors 804. Similarly, the method described herein can be implemented at least in part by a processor, wherein one or more specific processors 804 are examples of hardware. For example, at least some operations of the method can be performed by one or more processors 804 or processor-implemented components. In addition, one or more processors 804 can also be operated to support the execution of related operations in a "cloud computing" environment or operate as "software as a service" (SaaS). For example, at least some operations can be performed by a group of computers (as an example of a machine 800 including a processor 804), wherein these operations can be accessed via a network 832 (e.g., the Internet) and via one or more appropriate interfaces (e.g., API). The execution of certain operations can be distributed between processors 804, not only residing in a single machine 800, but also deployed in multiple machines 800. In some example embodiments, the processor 804 or processor-implemented components may be located in a single geographic location (e.g., in a home environment, an office environment, or a server farm). In other example embodiments, the processor 804 or processor-implemented components may be distributed across multiple geographic locations.

[0120] A "processor" in this context refers to any circuit or virtual circuit (a physical circuit simulated by logic executed on an actual processor) that manipulates data values ​​according to control signals (e.g., "commands," "opcodes," "machine codes," etc.) and produces corresponding output signals applied to operate the machine 800. For example, the processor 804 may be a central processing unit (CPU), a reduced instruction set computing (RISC) processor, a complex instruction set computing (CISC) processor, a graphics processing unit (GPU), a digital signal processor (DSP), an ASIC, a radio frequency integrated circuit (RFIC), or any combination thereof. The processor may also be a multi-core processor having two or more independent processors 804 (sometimes referred to as "cores") that can execute instructions 810 simultaneously.

[0121] Notes

[0122] The present disclosure includes, but is not limited to, the following schemes.

[0123] 1. A method comprising:

[0124] receiving a first set of listing data from a client device for use in generating a display of items for sale on an online marketplace;

[0125] determining, based on the first set of listing data, a first likelihood value indicative of a likelihood that the display will result in a sale within a given time period; and

[0126] A graphical indicator is caused to be presented on a display of the client device, the graphical indicator representing the first likelihood value.

[0127] 2. The method according to claim 1, further comprising:

[0128] receiving a second set of listing data from the client device to generate the display after causing the graphical indicator to be presented;

[0129] determining, based on the first set of listing data and the second set of listing data, an updated likelihood value indicative of a likelihood that the display will result in a sale within a given time period; and

[0130] A presentation of the graphical indicator on the display of the client device is updated to represent the updated likelihood value.

[0131] 3. The method of claim 1, wherein the graphical indicator is a graphical representation of a dial indicator, the dial indicator comprising a pointer within the dial indicator for representing the first likelihood value.

[0132] 4. The method according to Option 1, wherein the graphical indicator is a two-dimensional graph, the two-dimensional graph including a first axis representing the likelihood value and a second axis representing the first time period, the first likelihood value being a function of the first time period.

[0133] 5. The method according to claim 1 further comprises:

[0134] determining, based on said first set of listing data, a suggested modification to be performed on a display of said item for sale;

[0135] determining an expected change in the first likelihood value resulting from implementing the suggested modification; and

[0136] A notification is caused to be presented on a display of the client device, the notification identifying the suggested modification and an expected change in the first likelihood value as a result of executing the suggested modification.

[0137] 6. The method according to claim 1, wherein the first set of list data includes values ​​of at least two list data fields.

[0138] 7. The method of claim 1, wherein the at least two listing data fields include an image of the item listed for sale.

[0139] 8. A system comprising:

[0140] one or more computer processors; and

[0141] One or more computer-readable media storing instructions that, when executed by the one or more computer processors, cause the system to perform operations comprising:

[0142] receiving a first set of listing data from a client device for use in generating a display of items for sale on an online marketplace;

[0143] determining, based on the first set of listing data, a first likelihood value indicative of a likelihood that the display will result in a sale within a given time period; and

[0144] A graphical indicator is caused to be presented on a display of the client device, the graphical indicator representing the first likelihood value.

[0145] 9. According to the system of scheme 8, the operation further includes:

[0146] receiving a second set of listing data from the client device to generate the display after causing the graphical indicator to be presented;

[0147] determining, based on the first set of listing data and the second set of listing data, an updated likelihood value indicative of a likelihood that the display will result in a sale within a given time period; and

[0148] A presentation of the graphical indicator on the display of the client device is updated to represent the updated likelihood value.

[0149] 10. The system of claim 8, wherein the graphical indicator is a graphical representation of a dial indicator, the dial indicator comprising a pointer within the dial indicator for representing the first likelihood value.

[0150] 11. A system according to Option 8, wherein the graphical indicator is a two-dimensional graph, the two-dimensional graph including a first axis representing the likelihood value and a second axis representing the first time period, the first likelihood value being a function of the first time period.

[0151] 12. The system according to solution 8, wherein the operation further comprises:

[0152] determining, based on said first set of listing data, a suggested modification to be performed on a display of said item for sale;

[0153] determining an expected change in the first likelihood value resulting from implementing the suggested modification; and

[0154] A notification is caused to be presented on a display of the client device, the notification identifying the suggested modification and an expected change in the first likelihood value resulting from executing the suggested modification.

[0155] 13. A system according to Option 8, wherein the first set of list data includes values ​​of at least two list data fields.

[0156] 14. The system of claim 8, wherein the at least two listing data fields include an image of the item listed for sale.

[0157] 15. A non-transitory computer-readable medium storing instructions that, when executed by one or more computer processors of one or more computing devices, cause the one or more computing devices to perform operations comprising:

[0158] receiving a first set of listing data from a client device for use in generating a display of items for sale on an online marketplace;

[0159] determining, based on the first set of listing data, a first likelihood value indicative of a likelihood that the display will result in a sale within a given time period; and

[0160] A graphical indicator is caused to be presented on a display of the client device, the graphical indicator representing the first likelihood value.

[0161] 16. The non-transitory computer readable medium of claim 15, wherein the operations further comprise:

[0162] receiving a second set of listing data from the client device to generate the display after causing the graphical indicator to be presented;

[0163] determining, based on the first set of listing data and the second set of listing data, an updated likelihood value indicative of a likelihood that the display will result in a sale within a given time period; and

[0164] A presentation of the graphical indicator on the display of the client device is updated to represent the updated likelihood value.

[0165] 17. The non-transitory computer-readable medium of claim 15, wherein the graphical indicator is a graphical representation of a dial indicator, the dial indicator comprising a pointer within the dial indicator for representing the first likelihood value.

[0166] 18. A non-transitory computer-readable medium according to Option 15, wherein the graphical indicator is a two-dimensional graph, the two-dimensional graph including a first axis representing the likelihood value and a second axis representing the first time period, the first likelihood value being a function of the first time period.

[0167] 19. The non-transitory computer readable medium of claim 15, wherein the operations further comprise:

[0168] determining, based on said first set of listing data, a suggested modification to be performed on a display of said item for sale;

[0169] determining an expected change in the first likelihood value resulting from implementing the suggested modification; and

[0170] A notification is caused to be presented on a display of the client device, the notification identifying the suggested modification and an expected change in the first likelihood value resulting from executing the suggested modification.

[0171] 20. The non-transitory computer-readable medium of claim 15, wherein the first set of list data comprises values ​​of at least two list data fields.

Claims

1. A method for providing display conversion optimization, comprising: receiving a first set of listing data from a client device for use in generating a display of items for sale on an online marketplace; using a machine learning model trained based on historical listing data, determining, based on the first set of listing data, a plurality of corresponding likelihood values ​​indicating a likelihood that the display will result in the item being sold within a plurality of given time periods; A graphical indicator is caused to be presented on a display of the client device, the graphical indicator representing the plurality of respective likelihood values ​​indicating a likelihood that the display will result in the item being sold within the plurality of given time periods.

2. The method according to claim 1, further comprising: receiving a second set of listing data from the client device to generate the display after causing the graphical indicator to be presented; determining, based on the first set of listing data and the second set of listing data, a plurality of updated respective likelihood values ​​indicative of a likelihood that the display will result in the item being sold within the plurality of given time periods; and A presentation of the graphical indicator on the display of the client device is updated to represent respective likelihood values ​​of the plurality of updates.

3. The method according to claim 1, further comprising: determining, using the machine learning model, a recommended modification to be performed on a display of the item for sale based on the first set of listing data; determining an expected change in the plurality of corresponding likelihood values ​​resulting from performing the suggested modification; as well as A notification is caused to be presented on a display of the client device, the notification identifying the suggested modification and an expected change in the plurality of corresponding likelihood values ​​as a result of executing the suggested modification.

4. The method according to claim 1, wherein: The graphical indicator is a two-dimensional graph including a first axis representing likelihood values ​​and a second axis representing time periods.

5. The method according to claim 1, wherein: The first set of list data includes values ​​of at least two list data fields.

6. The method according to claim 5, wherein: The at least two listing data fields include images of the item listed for sale.

7. The method according to claim 3, wherein: It was determined that the proposed modifications to be implemented in the display of said items for sale included: identifying the model feature having the greatest negative impact on the first likelihood value; and generating a suggested modification to improve a specified characteristic of the article based on the identified model characteristics; and Wherein, the first likelihood value is one of the multiple corresponding likelihood values.

8. The method according to claim 1, wherein: The machine learning model is configured to output data indicating a positive impact of various model features on the likelihood value.

9. A system for providing display conversion optimization, comprising: one or more computer processors; as well as One or more computer readable media storing instructions which, when executed by the one or more computer processors, cause the system to perform the method of any one of claims 1 to 8.

10. A non-transitory computer readable medium storing instructions which, when executed by one or more computer processors of one or more computing devices, cause the one or more computing devices to perform the method of any one of claims 1 to 8.

Images