Information processing device, information processing method, and information processing program

Abstract

Efficiently select products to advertise. [Solution] The information processing device acquires first data including the number of impressions and clicks for each of the ad pages of multiple products over a predetermined period, and second data including the purchase history of the products advertised on the ad pages clicked over the predetermined period. Using the first data and the second data, it calculates a product quality score that represents the balance between CVR (Conversion Rate) and CTR (Click Through Rate) for each of the multiple products over the predetermined period, and selects a predetermined number of products to be advertised from the multiple products based on the product quality score.

Description

[Technical Field]

[0001] This invention relates to a technology for selecting products to be featured in advertisements. [Background technology]

[0002] In recent years, electronic commerce (E-commerce), which involves selling goods online using the internet, has become increasingly popular. Such E-commerce is often conducted through marketplaces (e.g., marketplace-type E-commerce sites) where multiple stores list and sell their products online. Users can access these marketplaces from their personal computers (PCs) or mobile devices such as smartphones, allowing them to browse and purchase desired products without having to physically visit multiple stores or being constrained by time.

[0003] Merchants selling products on marketplaces use various online advertising platforms to advertise their products in order to increase their Conversion Rate (CVR). CVR is a metric that represents the ratio of the number of conversions (purchases, contracts, etc.) that the merchant anticipates to achieve to the number of visits (also called sessions) to a webpage (in this case, a product page for selling products). Online advertising platforms are platforms for placing and delivering advertisements online (i.e., on webpages) and for providing advertising analytics services, and are provided by web services such as Google, Facebook, and Yahoo. Merchants can use online advertising platforms to deliver advertisements for products that may be relevant to the interests of users (i.e., webpage viewers) through various channels provided by the web service (e.g., video site channels, news site channels, hobby and interest site channels).

[0004] When delivering advertisements for products using an advertisement page on an online advertising platform (for example, a page assigned to an advertisement that occupies at least a partial area of a web page viewed by a user), considering the merchant's profit, it is effective to deliver advertisements for products with a high conversion rate (CVR). On the other hand, since the operator of the online advertising platform charges the merchant according to the number of clicks on the advertisement page of the product (that is, levies an advertising fee), considering the operator's profit, it is effective to deliver advertisements for products with a high click-through rate (CTR). CTR is a numerical value indicating the ratio of the number of clicks to the number of impressions on a web page (that is, the number of times the web page is displayed). For a merchant, even if the CVR is high and the CTR is also high, the advertising cost increases relative to the profit from product sales, and the overall revenue decreases. Therefore, there is a need for a technology for creating advertisements considering CVR and CTR. A technology for creating advertisements considering CVR and CTR is disclosed in, for example, Patent Document 1.

Prior Art Documents

Patent Documents

[0005]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0006] The above document discloses a technology for creating advertisements considering CVR and CTR. However, a mechanism for efficiently selecting one or more products to be advertised considering the balance between CVR and CTR among a plurality of candidate products targeted for advertisements has not been proposed so far.

[0007] The present invention has been made in view of the above problems, and an object thereof is to provide a technology for efficiently selecting products to be advertised.

Means for Solving the Problems

[0008] To solve the above problems, one aspect of the information processing apparatus according to the present invention includes: a first data acquisition unit that acquires first data including the number of impressions and clicks for each of the advertising pages of a plurality of products over a predetermined period; a second data acquisition unit that acquires second data including the purchase history of products advertised on the advertising pages clicked over the predetermined period; a calculation unit that uses the first data and the second data to calculate a product quality score representing the balance between CVR (Conversion Rate) and CTR (Click Through Rate) for each of the plurality of products over the predetermined period; and a selection unit that selects a predetermined number of products to be advertised from the plurality of products based on the product quality score.

[0009] To solve the above problems, one aspect of the information processing method according to the present invention includes: acquiring first data including the number of impressions and clicks for each advertising page of a plurality of products over a predetermined period; acquiring second data including the purchase history of products advertised on the advertising pages clicked over the predetermined period; using the first data and the second data to calculate a product quality score representing the balance between CVR (Conversion Rate) and CTR (Click Through Rate) for each of the plurality of products over the predetermined period; and selecting a predetermined number of products to be advertised from the plurality of products based on the product quality score.

[0010] To solve the above problems, one aspect of the information processing program according to the present invention is an information processing program for causing a computer to perform information processing, the program for causing the computer to perform the following processes: a first data acquisition process for acquiring first data including the number of impressions and clicks for each of the advertising pages of a plurality of products over a predetermined period; a second data acquisition process for acquiring second data including the purchase history for products advertised on the advertising pages clicked over the predetermined period; a calculation process for calculating a product quality score that represents the balance between CVR (Conversion Rate) and CTR (Click Through Rate) for each of the plurality of products over the predetermined period using the first data and the second data; and a selection process for selecting a predetermined number of products to be advertised from the plurality of products based on the product quality score. [Effects of the Invention]

[0011] According to the present invention, it becomes possible to efficiently select products to advertise. The objects, embodiments, and effects of the present invention described above, as well as any other objects, embodiments, and effects of the present invention not described above, can be understood by those skilled in the art from the following embodiments for carrying out the invention by referring to the accompanying drawings and the claims. [Brief explanation of the drawing]

[0012] [Figure 1] Figure 1 shows an example of the configuration of an information processing system according to an embodiment. [Figure 2] Figure 2 shows a conceptual diagram of the overall processing by the product list management device, marketplace operation device, and advertising distribution device. [Figure 3] Figure 3 shows an example of the functional configuration of a product list management device according to an embodiment. [Figure 4] Figure 4 shows an example of the hardware configuration of a product list management device according to an embodiment. [Figure 5] Figure 5 shows a flowchart of the processes performed by the product list management device according to the embodiment. [Figure 6] Figure 6 shows an example of a product quality score. [Modes for carrying out the invention]

[0013] Hereinafter, embodiments for carrying out the present invention will be described in detail with reference to the attached drawings. Among the components disclosed below, those having the same function are denoted by the same reference numeral, and their descriptions are omitted. The embodiments disclosed below are merely examples of means for realizing the present invention, and should be modified or changed as appropriate depending on the configuration of the apparatus to which the present invention is applied and various conditions, and the present invention is not limited to the embodiments below. Furthermore, not all combinations of features described in these embodiments are essential for solving the problem of the present invention.

[0014] [Configuration of the Information Processing System] Figure 1 shows an example of the configuration of the information processing system 1 according to this embodiment. The information processing system 1 is composed of a product list management device 10, a marketplace operation device 11, an advertising distribution device 12, and a user device 13. The product list management device 10, the marketplace operation device 11, the advertising distribution device 12, and the user device 13 function as information processing devices configured to communicate with each other via a network 14. The network 14 can include the internet, an intranet, a LAN (Local Area Network), a WAN (Wide Area Network), a mobile communication network, etc. Although Figure 1 shows one user device 13, the information processing system 1 has multiple user devices (not shown) that have the same functions as the user device 13, and these multiple user devices are configured to communicate with the product list management device 10, the marketplace operation device 11, and the advertising distribution device 12 via the network 14. The user device 13 is operated by a user 15. In this disclosure, the terms user device and user may be understood as synonymous. Furthermore, the product list management device 10 and the advertising distribution device 12 may be configured as a single device. Also, the term "product" may be understood as a term that includes at least information that can identify a product.

[0015] The marketplace operator 11 is a server device that operates and provides a marketplace (for example, an e-commerce site such as a marketplace-type e-commerce site) where multiple stores sell products by listing them online. For example, the marketplace operator 11 operates an e-commerce mall that develops a shopping mall through sales pages (web pages) of products sold by multiple merchants. The marketplace operator 11 can receive access from the user device 13 via the network 14 and provide various services related to shopping on the marketplace to the user 15. For example, when the user 15 accesses the marketplace and takes an action such as purchasing or viewing on the product page of any product (i.e., the online sales page of the product; the same applies hereinafter), the marketplace operator 11 provides services related to that product to the user 15. Note that the marketplace operator 11 is not limited to a server device and may be implemented using a mainframe or the like.

[0016] The ad distribution device 12 is a server device that provides an online advertising platform (hereinafter referred to as the advertising platform) and distributes advertisements. The advertising platform is a platform for online advertisement placement and distribution, as well as advertising analysis services. The ad distribution device 12 can place (i.e., upload) advertisements in the form of banners, etc., on multiple online channels (for example, video site channels, news site channels, hobby and preference site channels, online map channels, and email channels) and distribute them. Merchants of the marketplace provided by the marketplace operating device 11 can distribute advertisements for their products using the advertising platform provided by the ad distribution device 12. When user 15 clicks on an advertisement page for any product distributed on an online channel (hereinafter referred to as a channel) displayed on user device 13 (for example, a page allocated to an advertisement that occupies at least a portion of the area of ​​a web page viewed by user 15; the same applies hereinafter), the page displayed on user device 13 moves to the landing page corresponding to that advertisement. For example, if user 15 clicks on an advertisement page for a product sold by a marketplace merchant provided by the marketplace operating device 11, the page displayed on user device 13 switches to the product page for that item.

[0017] The ad distribution device 12 can, for example, display advertisements for products on one or more channels selected by the merchant. The merchant can select the channels on which to display advertisements, taking into account the target users (i.e., the purchasing demographic) of the products they sell. Since the conversion rate (CVR) and click-through rate (CTR) may increase or decrease depending on the channels on which the advertisements are displayed, it is desirable to select the channels appropriately. In addition to, or instead of, the merchant selecting the channels on which to display advertisements, the ad distribution device 12 or the marketplace operator 11 may select the channels on which to display advertisements. Furthermore, the ad distribution device 12 or the marketplace operator 11 may determine the channels on which to display advertisements using machine learning based on user attributes (e.g., demographic information) and historical information (e.g., information on visit and purchase activities on web pages, as described later) obtained from each user. Note that the ad distribution device 12 is not limited to a server device and may be implemented using a mainframe or the like.

[0018] User device 13 is operated by user 15, and can access the marketplace provided by marketplace operator 11 and receive various services. For example, user 15 can operate user device 13 to access the marketplace, view product pages for various products offered in the marketplace, and purchase products on product pages. In this embodiment, when user 15 clicks on an advertisement page for a product distributed by the advertisement distribution device 12 displayed on user device 13 (including the operation of selecting an advertisement page displayed on the screen), the page displayed on user device 13 moves from the advertisement page to the landing page corresponding to the advertisement, i.e., the product page of the product on the advertisement page. That is, when user 15 clicks on any advertisement page, they can access the product page of the product on the clicked advertisement page in the marketplace provided by marketplace operator 11. In this embodiment, it is assumed that the user moves directly to the landing page in response to a click on the advertisement page, but the user may also move to the landing page in response to step-by-step clicks on web pages to which they have moved in response to a click on the advertisement page.

[0019] The user device 13 is, for example, a smartphone or tablet, and is configured to communicate with the product list management device 10, the marketplace operation device 11, and the advertising distribution device 12 via the network 14. The user device 13 has a display unit (display surface) such as an LCD display, and the user 15 can view information such as web pages displayed on the display unit. In addition, the user 15 can perform various operations using the GUI (Graphical User Interface) equipped on the display unit. These operations include various operations on content such as images displayed on the screen, such as tapping, sliding, and scrolling using a finger or stylus. The user device 13 may also have a separate display unit.

[0020] The marketplace operator 11 and the advertising distribution device 12 are configured to collect various data in response to interactions with the user 15 on the web page via the user device 13. The marketplace operator 11 and the advertising distribution device 12 each provide the collected data to the product list management device 10. The data collected by the marketplace operator 11 and the advertising distribution device 12 will be described below. In the following description, data collected in response to interactions with the user 15 will be described, but the marketplace operator 11 and the advertising distribution device 12 can collect data in response to interactions with multiple users, including user 15, via multiple user devices, and provide this data to the product list management device 10.

[0021] The marketplace operator 11 collects user 15's actions when viewing product pages as visit activity. Visit activity is data representing user 15's actions on product pages of products sold in the marketplace. Visit activity can include, for example, the number of accesses to product pages, the time spent on product pages, the page bounce rate, and other behavioral patterns. The marketplace operator 11 also collects purchases by user 15 as purchase activity (also referred to as purchase history) as an example of conversion to products. Purchase activity occurs when user 15 purchases a product, and is registered as 1 (conversion occurred) if a purchase occurred, and 0 (no conversion) if no purchase occurred. Purchase activity occurs, for example, when user 15 adds a product to their cart on a product page, enters the required information, and completes payment to purchase the product (i.e., performs a purchase action). The marketplace operator 11 collects visit activity and purchase activity as activity data and provides the collected activity data to the product list management device 10.

[0022] The ad distribution device 12 collects the number of times an ad page is displayed on the user device 13 as the number of impressions, and the number of times a user 15 clicks on an ad page as the number of clicks. The ad distribution device 12 can collect the number of impressions and the number of clicks as ad performance data (hereinafter referred to as performance data) for the ad page. The performance data can be used to calculate the CTR. CTR is a numerical value that indicates the ratio of clicks to impressions for a web page. In this embodiment, the CTR corresponds to a numerical value that indicates the ratio of clicks to impressions for the ad page of a product distributed by the ad distribution device 12. The ad distribution device 12 provides the collected performance data to the product list management device 10. The ad distribution device 12 may also calculate the CTR and include it in the performance data provided to the product list management device 10.

[0023] In this embodiment, when users are directly redirected to a landing page (i.e., a product page) in response to a click on an advertisement page, the number of accesses to the product page and the number of clicks to the advertisement page have the same meaning and will be the same number. That is, the number of accesses included in the visit activity in the activity data and the number of clicks included in the performance data have the same meaning and will be the same number. On the other hand, when users are redirected to a landing page in response to a step-by-step click on a webpage after clicking on an advertisement page, the number of accesses to the product page and the number of clicks to the advertisement page may not be the same number. That is, the number of accesses included in the visit activity in the activity data and the number of clicks included in the performance data may not be the same number.

[0024] The product list management device 10 acquires and maintains a list (hereinafter referred to as the merchant product list) of multiple (N items (where N is a natural number of 2 or more)) products that each merchant can sell in the marketplace operated by the marketplace operator 11. The merchant product list may be catalog data of the products offered by each merchant. The marketplace operator 11 may also manage the merchant product list and provide it to the product list management device 10. The products included in the merchant product list may be updated, for example, at regular intervals, and such updates may be performed by the product list management device 10 or the marketplace operator 11 at the direction of the merchant.

[0025] The product list management device 10 acquires performance data from the advertising distribution device 12 and activity data from the marketplace operation device 11. Based on the merchant product list, performance data, and activity data, the product list management device 10 calculates a product quality score for each of the N products included in the merchant product list. In this embodiment, the product quality score is a score that indicates product quality (or product advertising quality) from the perspective of CVR and CTR, and corresponds to a score that represents the balance between CVR and CTR. That is, the product quality score corresponds to the cost that represents the balance between both conversion and advertising cost, and the higher the score, the higher the balance, specifically meaning that the CVR and CTR are relatively high. The product list management device 10 calculates the product quality score using the actual conversion score (CV score) and CTR for the product. The CV score is a score that represents a conversion, expressed as 1 (conversion occurred) or 0 (no conversion). Products with a high product quality score can be expected to have a high CVR and a high CTR, i.e., low advertising cost, which is beneficial for merchants. Furthermore, given the expected high click-through rate (CTR), this product can also be beneficial to operators of advertising platforms.

[0026] Then, the product list management device 10 selects, as a predetermined number of products to be advertised, a predetermined M products (M < N, where N is a natural number) out of the N products included in the merchant product list. Then, a list of the selected M products is constructed (generated) as an optimized product list, and the optimized product list is provided to the advertisement distribution device 12. The product list management device 10 can perform such processes of calculating the product quality score, selecting products, constructing, and providing the optimized product list for each merchant. The procedure for calculating the product quality score will be described later.

[0027] The advertisement distribution device 12 that has acquired the optimized product list posts and distributes the advertisements of the M products included in the list to each channel. Which channel to post the advertisements of each of the M products may be determined by any method including machine learning. The advertisement distribution device 12 can perform such acquisition of the optimized product list and distribution of the advertisements of each of the M products for each merchant.

[0028] A conceptual diagram of the overall processing by the product list management device 10, the marketplace operation device 11, and the advertisement distribution device 12 according to this embodiment is shown in FIG. 2. S20 represents the processing in the product list management device 10, S21 represents the processing in the advertisement distribution device 12, and S22 represents the processing in the marketplace operation device 11. FIG. 2 will be described in the order of the processing of S21, S22, and S20. Refer to FIG. 1 for the description of FIG. 2.

[0029] In this embodiment, a predetermined period (hereinafter referred to as the target period) for calculating the product quality score for each of the N products is set in advance. The advertising distribution device 12 and the marketplace operation device 11 each collect performance data and activity data during the target period and provide them to the product list management device 10. The product list management device 10 then calculates the product quality score for each of the N products during the target period. For example, if the product quality score is calculated on a daily basis, the target period will be a predetermined one-day period. The target period may be set in advance in the product list management device 10, set by an operator, or set by a predetermined program.

[0030] In S21, the ad distribution device 12 provides multiple channels on the advertising platform. In the example in Figure 2, a search site channel 211, an email channel 212, and a map site channel 213 are shown. The ad distribution device 12 can distribute ad pages by posting (i.e., uploading) product advertisements to at least one of the search site channel 211, the email channel 212, and the map site channel 213. The ad distribution device 12 collects the number of clicks and impressions for the ad pages on each channel during the target period, generates performance data including the collected clicks and impressions, and provides it to the product list management device 10. The ad distribution device 12 can also obtain an optimization list from the product list management device 10 and distribute ad pages by posting advertisements for M (or more) products included in the optimization list to at least one of the search site channel 211, the email channel 212, and the map site channel 213.

[0031] In S22, the marketplace operating device 11 collects visit activity and purchase activity during the target period on the product pages of the marketplace it provides, generates activity data including the collected visit activity and purchase activity, and provides it to the product list management device 10. In this embodiment, the product page corresponds to a landing page displayed on the user device 13 when the user 15 clicks on an advertising page provided by the advertising distribution device 12.

[0032] In S20, the product list management device 10 obtains a merchant product list from the merchant. The product list management device 10 may also obtain the merchant product list from the merchant via another device. The product list management device 10 then calculates a product quality score for the target period using performance data obtained from the advertising distribution device 12 and activity data obtained from the marketplace operation device 11. The procedure for calculating the product quality score will be described later. The product list management device 10 then constructs an optimized product list for the target period by optimizing the merchant product list using the calculated product quality score. Furthermore, the product list management device 10 provides the constructed optimized product list to the advertising distribution device 12.

[0033] [Configuration of the product list management system] Figure 3 shows an example of the functional configuration of the product list management device 10 according to this embodiment. The product list management device 10 includes, as an example of its functional configuration, a performance data acquisition unit 301, an activity data acquisition unit 302, a score calculation unit 303, a list optimization unit 304, a product list storage unit 310, and a parameter storage unit 320. The product list storage unit 310 is configured to store a merchant product list 311 and an optimized product list 312 for each merchant. In Figure 3, the merchant product list 311 and optimized product list 312 for a certain merchant are shown. The parameter storage unit 320 is configured to store various parameters used to calculate the product quality score.

[0034] The performance data acquisition unit 301 acquires performance data from the ad distribution device 12 for the target period. The performance data includes the number of clicks and impressions during the target period. The activity data acquisition unit 302 acquires activity data from the marketplace operating device 11 for the target period. The activity data includes visit activity and purchase activity during the target period.

[0035] The score calculation unit 303 calculates a product quality score for each of the N products during the target period using performance data and activity data obtained from multiple users, including user 15. In this embodiment, the score calculation unit 303 calculates the product quality score based on a bandit algorithm. A bandit algorithm is an algorithm classified as reinforcement learning within machine learning, and it aims to maximize rewards while balancing "exploitation" and "exploration". In this embodiment, the score calculation unit 303 calculates the product quality score based on the UCB (Upper-Confidence Bound) algorithm, which is a bandit algorithm. In the UCB algorithm, the reward is obtained by adding an estimated upper limit score (a value indicating "exploration") that indicates uncertainty to a score based on actual data (a value indicating "exploitation"). In this embodiment, as the estimated upper limit score indicating uncertainty, a score is used that is weighted by a weight representing uncertainty (specifically, a weight value indicating the score upper limit) to the estimated score.

[0036] The score calculation unit 303 calculates a predicted UCB for each product according to the UCB algorithm, representing the predicted upper limit CV (the upper limit of the predicted conversion (e.g., purchase)). cv (Hereinafter, PUCB cv (referred to as) and the predicted upper limit CTR (upper limit of the predicted CTR), which is the predicted UCB.ctr (Hereinafter, it is referred to as "PUCB" ctr ) is calculated. The predicted upper limit CV may be understood as the predicted upper limit CVR representing the upper limit of the predicted CVR. And the score calculation unit 303 multiplies cv PUCB ctr by cvtr PUCB

[0037] PUCB cv by ctr PUCB cv to calculate the product quality score cv PUCB cv (i).

Equation

[0038] CV(i) is the actual CV score for product i. The score calculation unit 303 can obtain CV(i) using the purchase activity included in the activity data for product i obtained from the marketplace operator 11. CV(i) is 1 if at least one of multiple users purchases product i during the target period, and 0 if none of the multiple users purchase product i. Ccv is a fixed value (hyperparameter) and is a parameter that controls machine learning for Mcv(i). N clk (i) is the number of clicks on the ad page for product i, Σ j N clk (j) is the total number of clicks on the ad pages for N products included in the merchant product list. The score calculation unit 303 calculates N from the number of clicks included in the performance data for product j (j=1~N) obtained from the ad distribution device 12. clk (i) and Σ j N clk (j) can be calculated.

[0039] Mcv(i) is the conversion rate (CV) score for product i estimated using a machine learning model. In this embodiment, the score calculation unit 303 can calculate Mcv(i) using a trained CV(i) estimation model. The CV(i) estimation model may be a machine learning model based on a CatBoost (Category Boosting) binary classification model to estimate whether product i can achieve at least one conversion. The CV(i) estimation model is pre-trained using the number of clicks on past advertising pages for product i and the purchase activity for product i, and the parameters for constructing the CV(i) estimation model derived through training are stored in the parameter storage unit 320. In this embodiment, the product list management device 10 pre-trains the CV(i) estimation model using the number of clicks and purchase activity collected before calculating the initial product quality score, generates parameters for constructing the model, and stores them in the parameter storage unit 320. Note that the training of the CV(i) estimation model may be performed by a device other than the product list management device 10.

[0040] Next, PUCB ctr This will be explained. The score calculation unit 303 calculates the PUCB for product i according to equation (2). ctr PUCB ctr Calculate (i).

number

[0041] CTR(i) is the actual click-through rate (CTR) for product i. The score calculation unit 303 can calculate CTR(i) using the number of impressions and clicks included in the performance data for product i obtained from the ad distribution device 12. Cctr(i) is a fixed value (hyperparameter) and is a parameter that controls machine learning for Mctr(i). imp (i) is the number of impressions for product i, Σ j N imp (j) is the total number of impressions for N products included in the merchant product list. The score calculation unit 303 calculates N from the number of impressions included in the performance data for product j (j=1~N) obtained from the ad distribution device 12. imp (i) and Σ j N imp (j) can be calculated.

[0042] Mctr(i) is the click-through rate (CTR) for product i estimated using a machine learning model. In this embodiment, the score calculation unit 303 can calculate Mctr(i) using a trained CTR(i) estimation model. The CTR(i) prediction model may be a machine learning model based on a CatBoost regression model. The CTR(i) estimation model is pre-trained using past click counts and impression counts for product i, and the parameters for constructing the CTR(i) prediction model derived through training are stored in the parameter storage unit 320. In this embodiment, the product list management device 10 pre-trains the CTR(i) estimation model using click counts and impression counts collected before calculating the initial product quality score, generates parameters for constructing the model, and stores them in the parameter storage unit 320. Note that the training of the CTR(i) estimation model may be performed by a device other than the product list management device 10.

[0043] The score calculation unit 303 calculates PUCB(i) cv and PUCB(i) ctr After calculating (3), the product quality score PUCB(i) of product i is calculated according to equation (3). cvtr This calculates PUCB(i). cv and PUCB(i) ctr By multiplying by , the product quality score PUCB(i) is obtained. cvtr Calculate.

number

[0044] The score calculation unit 303 calculates the product quality score PUCB(i) for all N products included in the merchant product list 311 during the target period. cvtr The score calculation unit 303 calculates the product quality score PUCB(i). cvtr This may be calculated periodically, for example, at the end of each target period. For example, if the target period is a predetermined one day, the score calculation unit 303 calculates the product quality score PUCB(i) cvtr You may calculate and update this daily.

[0045] The list optimization unit 304 calculates the product quality score PUCB(i) for the N products included in the merchant product list 311. cvtr Based on this, a predetermined number of M(N>N) products to advertise are selected from N products. In this embodiment, the list optimization unit 304 uses the product quality score PUCB(i) cvtr The products are sorted in descending order of score, and M products with the highest scores are selected. However, the selection is not limited to M products with the highest scores; for example, the list optimization unit 304 may select (Mm) products with higher scores (M>m) and m products with lower scores in order to verify the balance between conversions and advertising costs.

[0046] The list optimization unit 304 may select M items for each target period. That is, the list optimization unit 304 selects M items based on the product quality score PUCB(i) for each target period. cvtr Each time the calculation is performed, M items may be selected. Additionally, or alternatively, the list optimization unit 304 may select M items for each of multiple target periods. For example, the list optimization unit 304 may select M items for each of multiple product quality scores PUCB(i) calculated for each of multiple target periods. cvtr Averaging these values, the averaged PUCB(i) cvtr You may select M items based on this. Also, M does not have to be a fixed number; it may be a variable number.

[0047] The list optimization unit 304 selects M products from the N products included in the merchant product list 311 and constructs a list of M products as the optimized product list 312. The list optimization unit 304 stores the optimized product list 312 in the product list storage unit 310 and calculates the product quality score PUCB(i) for the N products. cvtr Each time the calculation is performed, the optimized product list 312 can be updated. The list optimization unit 304 provides the constructed optimized product list 312 to the advertising distribution device 12.

[0048] [Hardware configuration of the product list management device] Next, an example of the hardware configuration of the product list management device 10 will be described. Figure 4 is a block diagram showing an example of the hardware configuration of the product list management device 10 according to this embodiment. The product list management device 10 according to this embodiment can be implemented on one or more computers, mobile devices, or any other processing platform. Referring to Figure 4, an example is shown in which the product list management device 10 is implemented on a single computer; however, the product list management device 10 according to this embodiment may be implemented on a computer system including multiple computers. The multiple computers may be connected to each other via a wired or wireless network.

[0049] As shown in Figure 4, the product list management device 10 may include a CPU (Central Processing Unit) 401, a ROM (Read Only Memory) 402, a RAM (Random Access Memory) 403, an HDD (Hard Disk Drive) 404, an input unit 405, a display unit 406, a communication interface 407, and a system bus 408. The product list management device 10 may also include external memory. The CPU 401 comprehensively controls the operation of the product list management device 10 and controls each component (402-407) via the system bus 408, which is a data transmission path.

[0050] ROM402 is a non-volatile memory that stores control programs and other information necessary for the CPU401 to execute processing. This program includes instructions (code) that cause the processing according to the above embodiment to be executed. This program may be stored in non-volatile memory such as HDD404 or SSD (Solid State Drive), or in external memory such as a removable storage medium (not shown). RAM 403 is volatile memory and functions as the main memory, work area, etc., of the CPU 401. In other words, when executing processing, the CPU 401 loads necessary programs, etc., from ROM 402 into RAM 403 and executes these programs, etc., to realize various functional operations. RAM 403 may include the product list storage unit 310 and parameter storage unit 320 shown in Figure 3.

[0051] HDD404 stores various data and information necessary for CPU401 to perform processing using programs, for example. Furthermore, HDD404 also stores various data and information obtained through processing performed by CPU401 using programs, for example. The input unit 405 consists of pointing devices such as a keyboard or mouse. The display unit 406 is comprised of a monitor such as a liquid crystal display (LCD). The display unit 406 may function as a GUI (Graphical User Interface) when configured in combination with the input unit 405.

[0052] Communication I / F 407 is an interface that controls communication between the product list management device 10 and external devices. Communication I / F 407 provides an interface to a network and performs communication with external devices via the network. Various data and parameters are sent and received between the external device and the communication I / F 407. In this embodiment, communication I / F 407 may perform communication via a wired LAN (Local Area Network) or a dedicated line compliant with a communication standard such as Ethernet (registered trademark). However, the network that can be used in this embodiment is not limited to this and may consist of a wireless network. This wireless network includes wireless PANs (Personal Area Networks) such as Bluetooth (registered trademark), ZigBee (registered trademark), and UWB (Ultra Wide Band). It also includes wireless LANs (Local Area Networks) such as Wi-Fi (Wireless Fidelity) (registered trademark) and wireless MANs (Metropolitan Area Networks) such as WiMAX (registered trademark). Furthermore, it includes wireless WANs (Wide Area Networks) such as 4G and 5G. Furthermore, the network only needs to connect each device in a way that allows it to communicate with one another, and the communication standards, scale, and configuration are not limited to those described above.

[0053] At least some of the functions of the product list management device 10 shown in Figure 3 can be realized by the CPU 401 executing a program. However, at least some of the functions of the product list management device 10 shown in Figure 3 may be operated as dedicated hardware. In this case, the dedicated hardware operates based on the control of the CPU 401.

[0054] Furthermore, the hardware configurations of the user device 13, the marketplace operating device 11, and the advertising distribution device 12 may be the same as those shown in Figure 4.

[0055] [Processing flow of the product list management system] Figure 5 shows a flowchart of the processes performed by the product list management device 10 according to this embodiment. In S51, the performance data acquisition unit 301 acquires performance data for the target period from the advertising distribution device 12, and the activity data acquisition unit 302 acquires activity data for the target period from the marketplace operation device 11.

[0056] In S52, the score calculation unit 303 calculates a product quality score for each of the N products during the target period based on performance data and activity data. The procedure for calculating the product quality score is as described above. In S53, the list optimization unit 304 constructs an optimized product list 312 by selecting M products to advertise from the N products based on the calculated product quality scores for each of the N products. The list optimization unit 304 may select M products for each target period, or it may select M products for multiple target periods. Then, in S54, the list optimization unit 304 provides the constructed optimized product list 312 to the advertising distribution device 12. As a result, the advertising distribution device 12 can generate and distribute advertising pages for the M products included in the optimized product list 312. When the product list management device 10 and the advertising distribution device 12 are configured as a single device, advertising pages for the M products included in the constructed optimized product list 312 can be distributed.

[0057] Through this process, the product list management device 10 can select products for advertising that have a high probability of conversion and a high click-through rate (CTR). In other words, it enables merchants to select appropriate products that balance conversions and advertising costs.

[0058] A conceptual diagram of products and product quality scores is shown in FIG. 6. In the example of FIG. 6, for products 60 and 61, product quality scores have been calculated. The product quality score of product 60 is 0.7, and the product quality score of product 61 is 0.4. Under such conditions, when the list optimization unit 304 selects either of the two products to construct an optimized product list, it can select product 60 which has a high product quality score. Although the price of product 60 is lower than that of product 61, because the product quality score of product 60 is higher, product 60 can be expected to have a high conversion probability and a high CTR, and high profits can be expected for both the advertisement distribution side (for example, the operator of the advertisement platform) and the product offering side (for example, the merchant).

[0059] In this way, in order to select M (M < N) products that can be expected to have a high conversion probability and a high CTR among N products as advertisement target products, the product list management device 10 can achieve advertisement distribution that is beneficial to both the advertisement distribution side and the product offering side, compared with the case of selecting advertisement target products based only on CVR or CTR. Also, since the product list management device 10 calculates the product quality score using the factual data collected by each of the advertisement distribution side and the product offering side which are independent institutions, it can select products that appropriately evaluate the advertisement cost and advertisement effect without being advantageous to either side, and the reliability of this selection is enhanced. Further, by distributing M advertisement pages which are less than N instead of the advertisement pages of all N products, the processing load of the advertisement distribution device 12 is reduced.

[0060] In the above embodiment, the product list is optimized for each merchant, but this is not limited to this, and the product list may be optimized for each category, such as by product category. For example, the product list management device 10 may calculate the product quality score for each of the N products included in a certain category according to the above procedure, and select N products to advertise based on the product quality scores. Alternatively, the product list may be optimized for each merchant and each category. For example, the product list management device 10 may calculate the product quality score for each of the N products that a certain merchant can sell and that are included in a certain category, according to the above procedure, and select N products to advertise based on the product quality scores. Furthermore, in the above embodiment, the target was products sold on a marketplace operated by the marketplace operating device 11, but this embodiment can be applied to any item that can be traded online, such as intangible services.

[0061] Furthermore, in the above embodiment, optimization may be performed using visit activity. For example, if the user is moved to a landing page in response to a series of clicks on a webpage after clicking on an advertising page, the PUCB shown in equations (1) and (2) can be used. cv and PUCB ctr When calculating this, the number of accesses to product pages included in the visit activity may be used instead of the number of clicks on advertising pages. In addition, weights can be calculated by quantifying the time spent on product pages, page bounce rate, and other behavioral patterns included in the visit activity, and the PUCB shown in equations (1) and (2) can be calculated. cv and PUCB ctr This may be reflected in the weights representing uncertainty in each case. For example, if the time spent on a product page is longer than a predetermined time, and / or the bounce rate is lower than a predetermined value, the product list management device 10 may determine the weights to be higher so that the weights representing uncertainty are higher. This increases the second term on the right-hand side of equations (1) and (2), resulting in a higher product quality score.

[0062] Furthermore, while the above embodiment describes an example of selecting products to advertise on an online advertising page, the means of advertising the selected products are not limited to online advertising pages, but may also be, for example, print media or other media.

[0063] Furthermore, in the above embodiment, PUCB is calculated using equation (1) with respect to the purchase activity on the product page which serves as the landing page. cv Although this calculation was performed, it is not limited to the product page if purchase activity for a product is obtained. For example, when a user 15 purchases a product using audio or other information notified to the user device 13 in response to a click on an advertisement page, the marketplace operator 11 may register the purchase activity for the product.

[0064] Although specific embodiments are described above, these embodiments are merely illustrative and not intended to limit the scope of the present invention. Apparatuses and methods described herein can be embodied in forms other than those described above. Furthermore, the embodiments described above can be appropriately omitted, substituted, and modified without departing from the scope of the present invention. Such omitted, substituted, and modified forms fall within the scope of the claims and their equivalents and are within the technical scope of the present invention.

[0065] This embodiment includes the following configuration. [1] An information processing device comprising: a first data acquisition unit that acquires first data including the number of impressions and clicks for each of the advertising pages of multiple products over a predetermined period; a second data acquisition unit that acquires second data including the purchase history of products advertised on the advertising pages clicked over the predetermined period; a calculation unit that uses the first data and the second data to calculate a product quality score for each of the multiple products over the predetermined period; and a selection unit that selects a predetermined number of products to be advertised from the multiple products based on the product quality score.

[0066] [2] The information processing apparatus according to [1], wherein the selection unit selects a predetermined number of products from the plurality of products in order of the product quality score.

[0067] [3] The calculation unit calculates a predicted upper limit CVR, which is the upper limit of the predicted CVR (Conversion Rate), and a predicted upper limit CTR, which is the upper limit of the predicted CTR (Click Through Rate), for each of the plurality of products using the first data and the second data, and calculates the product quality score by multiplying the predicted upper limit CVR and the predicted upper limit CTR, as described in [1] or [2].

[0068] [4] The selection unit selects a predetermined number of products from the plurality of products each time a product quality score is calculated for each of the plurality of products, according to any one of [1] to [3].

[0069] [5] The selection unit selects a predetermined number of products from the plurality of products each time a plurality of product quality scores are calculated for each of the plurality of products, according to any one of [1] to [3].

[0070] [6] The information processing apparatus according to any one of [1] to [5], further comprising an advertising distribution unit for distributing advertisements for a predetermined number of products. [Explanation of Symbols]

[0071] 10: Product list management device, 11: Marketplace operation device, 12: Ad distribution device, 13: User device, 14: Network, 15: User, 301: Performance data acquisition unit, 302: Activity data acquisition unit, 303: Score calculation unit, 304: List optimization unit, 310: Product list storage unit, 311: Merchant product list, 312: Optimized product list, 320: Parameter storage unit

Claims

1. A first data acquisition unit acquires first data including the number of impressions and clicks for each advertising page of multiple products over a predetermined period, A second data acquisition unit acquires second data including purchase history for products advertised on ad pages clicked during the predetermined period, A calculation unit that uses the first data and the second data to calculate a product quality score representing the balance between CVR (Conversion Rate) and CTR (Click Through Rate) for each of the multiple products during the predetermined period, A selection unit that selects a predetermined number of products to be advertised from the plurality of products based on the product quality score, An information processing device having

2. The selection unit selects a predetermined number of products from the plurality of products in order of the highest product quality score. The information processing apparatus according to claim 1.

3. The calculation unit uses the first data and the second data to calculate a predicted upper limit CVR, which is the upper limit of the predicted CVR, and a predicted upper limit CTR, which is the upper limit of the predicted CTR, for each of the multiple products, and calculates the product quality score by multiplying the predicted upper limit CVR and the predicted upper limit CTR. The information processing apparatus according to claim 1.

4. The selection unit selects a predetermined number of products from the plurality of products each time a product quality score is calculated for each of the plurality of products. The information processing apparatus according to claim 1.

5. The selection unit selects a predetermined number of products from the plurality of products each time a plurality of product quality scores are calculated for each of the plurality of products. The information processing apparatus according to claim 1.

6. The system further includes an advertising distribution unit that distributes advertisements for a predetermined number of products. The information processing apparatus according to claim 1.

7. An information processing method performed by an information processing device, Obtaining first data including the number of impressions and clicks for each advertising page of multiple products over a specified period, The acquisition of second data, including purchase history for products advertised on ad pages clicked during the aforementioned predetermined period, Using the first data and the second data, a product quality score is calculated that represents the balance between CVR (Conversion Rate) and CTR (Click Through Rate) for each of the multiple products during the predetermined period. Based on the aforementioned product quality score, a predetermined number of products to be advertised are selected from the aforementioned multiple products, Information processing methods, including those mentioned above.

8. An information processing program for causing a computer to perform information processing, wherein the program causes the computer to perform information processing. A first data acquisition process that obtains first data including the number of impressions and clicks for each advertising page of multiple products over a predetermined period, A second data acquisition process that acquires second data including purchase history for products advertised on ad pages clicked during the predetermined period, A calculation process that uses the first data and the second data to calculate a product quality score representing the balance between CVR (Conversion Rate) and CTR (Click Through Rate) for each of the multiple products during the predetermined period, This process includes a selection process that selects a predetermined number of products to be advertised from the plurality of products based on the product quality score. Information processing program.

Images