JP6767824B2 - Judgment device, judgment method and judgment program - Google Patents

Description

The present invention relates to a determination device, a determination method, a determination program, a generation device, a generation method, and a generation program.

In recent years, with the development of communication networks, various services have been provided via networks. Examples of services via networks include financial services such as lending to companies and individuals and issuing credit cards.

For example, as a technique related to credit card payment, there is known a credit examination system capable of performing credit examination of credit card payment using a portable information processing device and a store terminal regardless of the amount of payment.

Japanese Unexamined Patent Publication No. 2013-246580

However, with the above-mentioned prior art, there are cases where the creditworthiness of an individual cannot be appropriately determined. Specifically, the above-mentioned prior art determines credit based on the card information regarding the issued credit card. Therefore, for example, when a new credit card is issued to an individual, the credit rating of the individual is determined. In some cases, the above technology cannot be applied.

The present application has been made in view of the above, and an object of the present application is to provide a determination device, a determination method, a determination program, a generation device, a generation method, and a generation program capable of appropriately determining an individual's creditworthiness. ..

The determination device according to the present application determines the creditworthiness of a user who intends to newly use a predetermined financial service based on an acquisition unit that acquires an action history on the user's network and an action history acquired by the acquisition unit. It is characterized in that it is provided with a determination unit.

According to one aspect of the embodiment, there is an effect that the creditworthiness of an individual can be appropriately determined.

FIG. 1 is a diagram showing an example of a determination process according to an embodiment. FIG. 2 is a diagram showing a configuration example of the determination system according to the embodiment. FIG. 3 is a diagram showing a configuration example of the determination device according to the embodiment. FIG. 4 is a diagram showing an example of a user information storage unit according to the embodiment. FIG. 5 is a diagram showing an example of an attribute information table according to the embodiment. FIG. 6 is a diagram showing an example of an action information table according to the embodiment. FIG. 7 is a diagram showing an example of a model storage unit according to the embodiment. FIG. 8 is a diagram showing an example of the condition information storage unit according to the embodiment. FIG. 9 is a flowchart (1) showing a processing procedure according to the embodiment. FIG. 10 is a flowchart (2) showing a processing procedure according to the embodiment. FIG. 11 is a hardware configuration diagram showing an example of a computer that realizes the function of the determination device.

Hereinafter, a determination device, a determination method, a determination program, a generation device, a generation method, and a mode for carrying out the generation program (hereinafter referred to as “the embodiment”) according to the present application will be described in detail with reference to the drawings. The determination device, the determination method, the determination program, the generation device, the generation method, and the generation program according to the present application are not limited by this embodiment. In addition, each embodiment can be appropriately combined as long as the processing contents do not contradict each other. Further, in each of the following embodiments, the same parts are designated by the same reference numerals, and duplicate description is omitted.

[1. Example of determination processing according to the embodiment]
First, an example of the determination process according to the embodiment will be described with reference to FIG. FIG. 1 is a diagram showing an example of a determination process according to an embodiment. FIG. 1 shows an example of a process in which the determination device 100 acquires user information via a network and determines the creditworthiness of a user who newly intends to use a predetermined financial service based on the acquired information.

The determination device 100 shown in FIG. 1 is a server device that determines the creditworthiness of a predetermined financial service for a user to be processed. The determination device 100 acquires predetermined information from the terminal used by the user, and performs a process of determining the creditworthiness of the user based on the acquired information.

User terminal 10 ₁ shown in FIG. 1 is an information processing terminal that is utilized by the user U01. The user terminal 10 ₂ is an information processing terminal that is utilized by the user U02. For example, the user terminal 10 ₁ and 10 ₂ is realized by a smart phone or tablet computer, or the like. In the following description, when it is not necessary to distinguish the user terminals 10 ₁ and 10 _2, referred to as user terminal 10 collectively. Further, in the following description, the user terminal may be replaced with the user. For example, it may mean that if the "user U01 sends a predetermined information to the determination device 100 'was expressed as, that" the user terminal 10 ₁ is transmitted to the determining unit 100 predetermined information according to the operation of the user U01 " is there.

In embodiments, the determination device 100 acquires the user information from the user terminal 10 ₁ and 10 _2. The user information includes a information held in the user terminal 10 ₁ and 10 _2, for example, and the action history of the network users U01 and user U02, the attribute information of the user U01 and the user U02. The action history on the network is, for example, the operation history performed by the user U01 or the user U02 on the Internet. Specifically, the action history on the network includes the history of search queries sent by user U01 or user U02 in the search service, the browsing history of websites, and the SNS (Social Networking Service) used by user U01 or user U02. ) Includes the history of posting articles and images. Further, the attribute information is information indicating the attributes of the user such as age, gender, place of residence, annual income, and presence / absence of spouse.

In the example of FIG. 1, the determination device 100 determines the creditworthiness of the user U02 who newly uses a predetermined financial service. Specifically, when the user U02 applies for the new issuance of a credit card (hereinafter, may be simply referred to as "card"), the determination device 100 determines the creditworthiness of the user U02 in the examination regarding the new issuance of the credit card. To judge.

Here, in the example of FIG. 1, it is assumed that the user U01 is a user who has received the issuance of the card to be applied for by the user U02 and has already used the service related to the card. Then, the user U01 is assumed to be a user who does not actively use the card, that is, a so-called negative user for the service.

For example, a negative user in a card service includes a user who does not use the card for shopping or the like even though the card is newly issued. For example, a card company may provide a privilege such as giving points that a user can use instead of cash when issuing a new card. A negative user is, for example, a user who receives only newly issued points and then uses only the received points and does not use the issued card. For negative users, for example, in financial services such as insurance, in addition to issuing cards, you can get benefits by applying only for quotation requests, or you can apply only for card switching requests and pamphlet sending requests to receive benefits. It also includes users who get it.

In this case, the card company cannot not only earn income from using the card, but also cannot recover various costs such as points related expenses, advertising expenses spent to enroll users, card issuance and card sending. It will be. That is, a business operator that provides financial services may suffer a disadvantage by subscribing to a negative user.

For this reason, it is important for businesses that provide financial services not to enroll negative users and to spend as little advertising expenses as possible on users who are likely to become negative users in the future. .. That is, a business that provides financial services determines what kind of users can be negative users, and changes the correspondence between users who are likely to be negative users and users who are unlikely to be negative users. Is desirable.

Therefore, the determination device 100 according to the embodiment compares the behavior history of the user U01, who is a user who has already used the service and is a negative user, with the behavior history of the user U02, who is not currently using the service. By doing so, the creditworthiness of the user U02 for the service is determined. More specifically, the determination device 100 determines whether or not the user U02 is a user who is likely to become a negative user like the user U01. As a result, the determination device 100 can efficiently perform processing related to user subscription of financial services. Hereinafter, such a determination process will be described along the flow with reference to FIG. In the example of FIG. 1, for the sake of simplicity, it is assumed that the determination device 100 itself provides the financial service related to card issuance.

In the example shown in FIG. 1, the determination unit 100 acquires information about the user U01 from the user terminal 10 ₁ (step S01). For example, the determination device 100 acquires the attribute information of the user U01 and the action history of the user U01 on the network as the information regarding the user U01. The determination device 100 includes a user information storage unit 121 that stores information about the user (hereinafter, may be referred to as "user information"), an attribute information table 122 that is a data table included in the user information storage unit 121, and an action. It is stored in the information table 123.

It is assumed that the determination device 100 determines the user U01 as a negative user in advance based on the card usage status of the user U01. For example, the determination device 100 determines the user U01 as a negative user from information such as a blacklist created by the administrator of the determination device 100.

Subsequently, the determination device 100 performs machine learning on the negative user using the user U01 as a positive example (step S02). That is, the determination device 100 uses the user U01 as a positive example to generate a model for determining a user similar to the user U01. In other words, the determination device 100 generates a model in which the user determined to be similar to the user U01 is determined to have a lower credit rating, and the user determined to be dissimilar to the user U01 is determined to have a higher credit rating.

For example, the determination device 100 outputs an index value such as how much the attribute information of the user U01 and the action history on the network are related to the attribute information newly input to the model and the action history on the network. Generate a model. Although not shown in FIG. 1, the determination device 100 has a predetermined sample amount (for example, 2000 or more) sufficient to give a certain reliability not only to the user U01 but also to the index value output by the model. (User, etc.) is acquired and a model is generated.

By using such a model, the determination device 100 may become a negative user based on the behavior history of a user who has newly applied for a service or a user who is a target for determining an advertisement for encouraging service subscription. Can be determined as to whether or not is high. That is, the determination device 100 determines that the higher the possibility that the new user becomes a negative user in the service currently used by the regular user, the lower the credit rating of the new user, and the new user. The lower the possibility that is a negative user, the higher the creditworthiness of the new user is judged. The determination device 100 stores the generated model in the model storage unit 124.

Then, the determining device 100, from the user terminal 10 _2, it is assumed to obtain information about the user U02 (step S03). For example, the determining device 100, as triggered by the user terminal 10 ₂ accepts the application for issuing new cards, to obtain information about the user U02. It is shown that the information about the user U02 in FIG. 1 is input to the user information storage unit 121 and also input to the model storage unit 124.

The determination device 100 determines the creditworthiness of the user U02 using the model (step S04). Specifically, the determination device 100 inputs information about the user U02 into the model generated in step S02. Then, the determination device 100 outputs an index value indicating how much the information about the user U02 is related (how similar) to the information of the user group determined to be a negative user in the service. .. The determination device 100 determines the creditworthiness of the user U02 in the service based on the index value.

Then, the determination device 100 notifies the user U02 of the result regarding the examination of card issuance based on the determination result (step S05). For example, if the credit rating of the user U02 is higher than the first threshold value, the determination device 100 permits the user U02 to issue the card under the condition that the full amount of points at the time of issuing the card is given. Alternatively, if the creditworthiness of the user U02 is lower than the first threshold value and higher than the second threshold value, the determination device 100 changes the condition to allow card issuance but reduce the points at the time of issuance by 50%. Alternatively, the determination device 100 may not allow the card issuance if the creditworthiness of the user U02 is lower than the second threshold value. In this way, the determination device 100 can take various measures based on the credit rating determined for the user U02.

In this way, the determination device 100 according to the embodiment acquires the action history of the user U01 and the user U02 on the network. Then, the determination device 100 determines the creditworthiness of the user U02 who intends to newly use the predetermined financial service based on the acquired action history of the user U01 and the user U02.

That is, the determination device 100 according to the embodiment determines a user who intends to newly use the service, using the behavior history of a user who is disadvantageous in the actually operating service such as a so-called negative user as a positive example. To do. Generally, in financial services, the examination is conducted based on the applicant's annual income, place of employment, etc. at the time of application for the service. However, it is difficult to judge a negative user who contracts a large number of cards only for the purpose of points, for example, based on his / her annual income or work place. On the other hand, the determination device 100 uses the action history on the network as a determination element. Here, it is assumed that a negative user is likely to browse a site where points are given free of charge, a site of an insurance company that can obtain benefits, or search for such a service. Therefore, according to the determination device 100, for example, by comparing the action history of the user U01 with the action history of the user U02, the user U02 who newly joins the service before joining the service will be in the future. It is possible to accurately determine whether or not there is a high possibility of becoming a negative user. That is, the determination device 100 can appropriately determine the creditworthiness of an individual in financial services.

In the example of FIG. 1, the determination unit 100 has been shown to acquire the user information of the user U01 and the user U02 from the user terminal 10 ₁ and 10 _2. The determining device 100, for example, by the user terminal 10 ₁ and 10 ₂ to crawl (crawl) every predetermined time may be acquired user information. Further, the determination device 100 may continuously acquire user information via a program (for example, an application dedicated to a smartphone) installed in the user terminal 10.

[2. Judgment system configuration]
Next, the configuration of the determination system 1 including the determination device 100 according to the embodiment will be described with reference to FIG. FIG. 2 is a diagram showing a configuration example of the determination system 1 according to the embodiment. As illustrated in FIG. 2, the determination system 1 according to the embodiment includes a user terminal 10, a web server 30, and a determination device 100. These various devices are connected via network N so as to be communicable by wire or wirelessly. Further, the number of each device included in the determination system 1 shown in FIG. 2 is not limited to that shown in the figure. For example, the determination system 1 may include a plurality of user terminals 10 and a web server 30.

As described above, the user terminal 10 is an information processing terminal such as a mobile phone including a smartphone, a tablet terminal, a desktop PC (Personal Computer), a notebook PC, or a PDA (Personal Digital Assistant). The user terminal 10 also includes a wearable device, which is a glasses-type or watch-type information processing terminal. Further, the user terminal 10 may include various smart devices having an information processing function for transmitting user information to the determination device 100. For example, the user terminal 10 may include smart home appliances such as TVs (Televisions), refrigerators, and vacuum cleaners, smart vehicles such as automobiles, drones, and domestic robots.

The web server 30 is a web server that delivers a service page such as a web page. For example, the web server 30 includes a portal site, a news site, an auction site, a weather forecast site, a shopping site, a finance (stock price) site, a route search site, a map providing site, a travel site, a restaurant introduction site, an SNS site, and a web blog. A web page containing various information related to the above is distributed to the user terminal 10.

The web page distributed by the web server 30 is formed by, for example, an HTML file described by HTML, an XML file described by XML (Extensible Markup Language), or the like. Further, the web page distributed by the web server 30 may include a content (advertisement) acquisition command. For example, in an HTML file or the like forming a web page, a URL or the like of a predetermined advertisement server is described as an advertisement acquisition command. In this case, the user terminal 10 acquires the advertisement content from the predetermined advertisement server by accessing the URL described in the HTML file or the like.

As described above, the determination device 100 is a server device that determines the creditworthiness of a user who newly intends to use a predetermined financial service based on user information such as an action history on the user's network.

[3. Configuration of determination device according to the embodiment]
Next, the configuration of the determination device 100 according to the embodiment will be described with reference to FIG. FIG. 3 is a diagram showing a configuration example of the determination device 100 according to the embodiment. As shown in FIG. 3, the determination device 100 includes a communication unit 110, a storage unit 120, and a control unit 130. The determination device 100 includes an input unit (for example, a keyboard, a mouse, etc.) that receives various operations from an administrator or the like who uses the determination device 100, and a display unit (for example, a liquid crystal display, etc.) for displaying various information. You may have.

(About communication unit 110)
The communication unit 110 is realized by, for example, a NIC (Network Interface Card) or the like. The communication unit 110 is connected to the network N by wire or wirelessly, and transmits / receives information to / from the user terminal 10 and the web server 30 via the network N.

(About storage unit 120)
The storage unit 120 is realized by, for example, a semiconductor memory element such as a RAM or a flash memory, or a storage device such as a hard disk or an optical disk. As shown in FIG. 3, the storage unit 120 includes a user information storage unit 121, a model storage unit 124, and a condition information storage unit 125.

(About user information storage unit 121)
The user information storage unit 121 stores user information. Here, FIG. 4 shows an example of the user information storage unit 121 according to the embodiment. FIG. 4 is a diagram showing an example of the user information storage unit 121 according to the embodiment. In the example shown in FIG. 4, the user information storage unit 121 has items such as "user ID", "terminal ID", "user determination", "attribute information", and "behavior information".

The "user ID" indicates identification information that identifies the user. The "terminal ID" indicates information that identifies the terminal used by the user. In the embodiment, the identification information shall match the reference code used for the explanation. For example, the user identified by the user ID "U01" indicates the user U01. The terminal identified by the terminal ID "10 _1" indicates the user terminal 10 _1.

“User determination” indicates information determined for a user in a predetermined financial service. As an example, user judgment is indicated by criteria such as "negative" or "non-negative". For example, the item of user determination may be artificially determined in advance and input as user information, or information may be input as appropriate according to the determination result by the model as described later. Further, for a user who has not been subjected to the determination process, the user determination item may be blank.

"Attribute information" indicates the attribute information of the user. "Behavior information" indicates the behavior information of the user. In the example of FIG. 4, attribute information and behavior information are shown by concepts such as "A01" and "B01", but these items include specific examples such as the user's gender, age, and place of residence. Information and specific information such as what kind of site you have visited may be stored. It should be noted that these specific information shall be appropriately stored in the data table described later.

That is, in the example of FIG. 4, the user U01 identified by the user ID "U01" indicates that using the user terminal 10 ₁ that is identified by the terminal ID "10 _1". Further, the user determination of the user U01 regarding the predetermined financial service is "negative", the attribute information of the user U01 is "A01", and the action information is "B01".

Further, the user information storage unit 121 has an attribute information table 122 and an action information table 123 as data tables.

(About attribute information table 122)
The attribute information table 122 stores the attribute information of the user among the user information. Here, FIG. 5 shows an example of the attribute information table 122 according to the embodiment. FIG. 5 is a diagram showing an example of the attribute information table 122 according to the embodiment. As shown in FIG. 5, the attribute information table 122 has items such as "user ID", "terminal ID", "attribute information", "gender", "age", "residential place", and "estimated annual income".

The "user ID" and "terminal ID" are the same as the items shown in FIG. "Attribute information" indicates the content of the user's attribute information. "Gender" indicates the gender of the user. "Age" indicates the age of the user. In the embodiment, the terminal ID may be treated as one of the attribute information. For example, a user may own a plurality of terminal devices. In this case, since the user can be identified by specifying a plurality of terminal devices owned by the user, the identification information for identifying these terminal devices may be treated as the attribute information of the user.

"Residence" indicates the user's residence. "Estimated annual income" indicates the estimated annual income of the user. In the example of FIG. 5, the place of residence and the estimated annual income are shown by concepts such as "E01" and "F01", but in reality, the item of the place of residence includes a specific user's address and network connection. The user's place of residence estimated from the situation is stored. Further, in the item of annual income, a specific value of annual income of the user estimated from the purchase history of the user is stored.

That is, in the example of FIG. 5, the attribute information of the user U01 to use the user terminal 10 _1, gender is "male", in the age of "30 years old", place of residence is "E01", the estimated annual income " It shows that it is "F01". The attribute information table 122 may store various attribute information such as the presence or absence of a spouse of the user, the birthplace and nationality of the user, and the like.

(About behavior information table 123)
The action information table 123 stores the user's action information (behavior history) among the user information. Here, FIG. 6 shows an example of the action information table 123 according to the embodiment. FIG. 6 is a diagram showing an example of the action information table 123 according to the embodiment. As shown in FIG. 6, the action information table 123 has items such as "user ID", "action information", "action date and time", "action type", "site", "card use", and "point use". ..

The "user ID" is the same as the item shown in FIG. "Behavior information" indicates the content of the user's behavior information. "Action date and time" indicates the date and time when the action was performed. "Behavior type" indicates the type of action taken by the user, such as browsing, purchasing, and searching. "Site" indicates a site (or a service page such as an application) targeted by an action.

"Card use" indicates information such as whether or not the card was used in the action. For example, the card use item indicates information as to whether or not the card contracted by the user U01 was used when the user U01 purchased a product on the shopping site. As for the item of card use, various different information may be stored depending on the service used by the user U01. For example, if the predetermined financial service used by user U01 is not a credit card contract but a securities account contract, the card use item may be replaced with an item such as "securities account use". Good.

"Point use" indicates information such as whether or not points have been used in the action. For example, the point use item indicates information such as how much of the consideration payable by the user U01 when the user U01 purchases a product on the shopping site is paid by the points.

That is, in an example of the behavior information of FIG. 6, the user U01 "purchases a product" at the "shopping site AAA" at "10:00 on July 15, 2016", and the card contracted by the user U01. Is "none" used, indicating that the points are used "100%" for accounting. Further, in another example, the user U01 indicates that he / she is "browsing" the "insurance estimation site" at "11:00 on August 20, 2016". In another example, the user U01 "purchases a product" at the "shopping site BBB" at "8:00 on September 25, 2016", and the card contracted by the user U01 is used "none". , Which indicates that the points are used "80%" for accounting.

(About model storage unit 124)
The model storage unit 124 stores information about the model generated by the determination device 100. Here, FIG. 7 shows an example of the model storage unit 124 according to the embodiment. FIG. 7 is a diagram showing an example of the model storage unit 124 according to the embodiment. As shown in FIG. 7, the model storage unit 124 has items such as "model ID", "learning data", "determination target", "determination result", "user ID", and "match rate".

The "model ID" indicates identification information that identifies the model. It is assumed that the model ID item includes not only the identification information but also the data of the model itself. “Training data” indicates sample data used to generate the model. In the example of FIG. 7, the training data is shown by a concept such as "N01", but in reality, the training data item contains information that is a positive example and a negative example in the model (for example, negative in a predetermined service). Information such as each user information of the user group determined to be a user, each user information of a user group not determined to be a negative user, and the number of samples used for model generation is stored. The learning data may be updated every time the sample data is acquired by the determination device 100.

The “judgment target” indicates the content such as what kind of user the model targets for the judgment. The "judgment result" indicates a judgment result when the model is applied to a predetermined user. The "user ID" indicates identification information that identifies the user. The "match rate" is a result output from the model when user information is input, and indicates a match rate with a correct example determined by the model. The concordance rate may be rephrased as an index value indicating the degree of similarity with the positive example determined by the model.

That is, in one example of FIG. 7, the model M01 identified by the model ID "M01" is a model generated (learned) based on the learning data "N01", and the determination target is the "card unused user". It shows that. Then, when the user information of the user U02 is input to the model M01, the user U02 has a matching rate of "58" with the correct example (in the example of FIG. 7, a card unused user, that is, a negative user in the service). It indicates that it was determined to be (%).

(About the condition information storage unit 125)
The condition information storage unit 125 stores information regarding conditions when a user newly subscribes to the service in a predetermined financial service. Here, FIG. 8 shows an example of the condition information storage unit 125 according to the embodiment. FIG. 8 is a diagram showing an example of the condition information storage unit 125 according to the embodiment. As shown in FIG. 8, the condition information storage unit 125 has items such as “model ID”, “condition ID”, “match rate”, and “content”.

The "model ID" indicates identification information that identifies a model for determining a condition when a user newly subscribes to the service in a predetermined financial service. The model ID corresponds to the same item shown in FIG. 7. The "condition ID" indicates identification information that identifies the condition set for the service subscription.

The "match rate" indicates the match rate when a user who newly subscribes to the service is determined by the model. "Content" indicates the content under each condition.

That is, in one example of FIG. 8, when the user determined by the model M01 has a match rate of "0 to 30", the condition G01 identified by the condition ID "G01" is applied, and the content thereof is "no condition". It shows that it is. Further, when the user determined by the model M01 has a matching rate of "31 to 50", the condition G02 is applied, and the content thereof is "20% reduction in granted points". This indicates that when a user subscribes to the service, the points awarded are reduced by 20% as compared with a normal user. Further, when the user determined by the model M01 has a matching rate of "51 to 70", the condition G03 is applied, and the content thereof is "a reduction of 50% of the granted points". Further, when the user determined by the model M01 has a match rate of "71 to 100", the condition G04 is applied, and the content thereof is "issue not permitted". This indicates that a user having a matching rate of "71 to 100" is likely to be a negative user, and therefore the service side does not allow the issuance of a credit card.

(About control unit 130)
The control unit 130 is, for example, a controller, and various programs (determination program or generation program) stored in a storage device inside the determination device 100 by a CPU (Central Processing Unit), an MPU (Micro Processing Unit), or the like. (Corresponding to one example) is realized by executing RAM (Random Access Memory) as a work area. Further, the control unit 130 is a controller, and is realized by, for example, an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

As shown in FIG. 3, the control unit 130 includes an acquisition unit 131, a generation unit 132, a determination unit 133, a determination unit 134, and a transmission unit 135, and functions and operations of information processing described below. To realize or execute. The internal configuration of the control unit 130 is not limited to the configuration shown in FIG. 3, and may be another configuration as long as it is a configuration for performing information processing described later. Further, the connection relationship of each processing unit included in the control unit 130 is not limited to the connection relationship shown in FIG. 3, and may be another connection relationship.

(About acquisition unit 131)
The acquisition unit 131 acquires various types of information. For example, the acquisition unit 131 acquires user information from the user terminal 10. Specifically, the acquisition unit 131 acquires the action history on the user's network.

For example, the acquisition unit 131 acquires information about a search query sent by the user to the search service as an action history on the user's network. More specifically, the acquisition unit 131 describes what kind of user is based on the similarity of the dictionary information indicated by the transmitted search query, the category and genre to which the search query belongs, the frequency of the transmitted search query, and the like. Get information that shows the tendency to send search queries frequently. In other words, the acquisition unit 131 acquires information on the user's interests from the transmission history of the search query.

In addition, the acquisition unit 131 acquires a history of the user browsing a predetermined service page as an action history on the user's network. Specifically, the acquisition unit 131 acquires the history of the website browsed by the user. In this case, the acquisition unit 131 acquires the history for each website category (for example, news site, shopping site, stock information site, etc.), and tends to determine what category of site the user frequently browses. Information indicating that may be acquired. In other words, the acquisition unit 131 acquires information on the user's interests from the browsing history of the website.

In addition, the acquisition unit 131 acquires the purchase history of the user in a predetermined service as the action history of the user on the network. Specifically, the acquisition unit 131 acquires the history of purchases of products and products by users on shopping sites, auction sites, travel reservation sites, etc., the categories and genres of purchased products, the frequency of purchasing behavior, and the like. .. In addition, the acquisition unit 131 determines the type of card used on the shopping site, the type of currency and points used, whether or not the account related to the service contracted by the user was used for payment, and the non-payment in payment. Information on various purchases may be obtained, such as whether there was a delay. In other words, the acquisition unit 131 acquires the user's characteristic information as to what kind of purchasing behavior the user is performing from the user's purchasing history in the predetermined service.

As described above, the acquisition unit 131 has at least information about the search query sent by the user to the search service, the browsing history of the user's predetermined service page, or the user's purchasing history in the predetermined service as the action history on the network. Get one of them. In addition to this, the acquisition unit 131 may further acquire the attribute information of the user as the user information. That is, the acquisition unit 131 acquires attribute information such as the user's gender, age, place of residence, and estimated annual income.

The acquisition unit 131 appropriately stores the acquired information in the user information storage unit 121 and each data table of the user information storage unit 121.

(About generator 132)
The generation unit 132 generates a model for examining a user who uses a predetermined financial service based on the action history acquired by the acquisition unit 131. Specifically, the generation unit 132 is based on at least one of information about a search query sent by the user to the search service, the browsing history of the user's predetermined service page, or the user's purchasing history in the predetermined service. To generate a model.

For example, the generation unit 132 generates a model based on the behavior history of a user who has a contract for a predetermined financial service and whose utilization rate of the predetermined financial service is lower than a predetermined threshold value. That is, the generation unit 132 generates a model for determining a user who has a high possibility of becoming a negative user, using the behavior history of a so-called negative user in a financial service as a positive example.

More specifically, the generation unit 132 generates a model for a financial service having a system for giving a predetermined point to a user among the predetermined financial services. For example, the generation unit 132 generates a model for a financial service having a system in which a predetermined point is given to a user when the service is subscribed. As a result, the generation unit 132 can generate a model capable of determining a negative user who is a user who hardly uses the financial service after receiving only the points that are the privilege at the time of subscription.

For example, the generation unit 132 receives the user's behavior history as input, and generates a model that outputs a predetermined index value indicating the rate at which the user having the behavior history matches the tendency of the behavior history of the positive example (negative user). .. The information output by the model is not limited to the match rate, and even if the model outputs the result of displaying in binary such as "1" and "0" whether or not it is similar to a negative user, for example. Good.

For example, the generation unit 132 sets the event that "the user is a negative user in the service" as an objective variable in machine learning, and sets the user's action history (specifically, each characteristic information constituting the action history) as a machine. It is used as an explanatory variable in learning. Then, the generation unit 132 generates a model showing the relationship between the determination result for the user and the user information (user's action history) by using the objective variable and the explanatory variable.

The generation unit 132 generates a model using various explanatory variables. As described above, in the determination device 100, for example, a user having what kind of action history is determined to be a "negative user" based on the determination of the manager of the determination device 100 or the financial service provider, and what kind of action history. Has correct answer data (sample data) as to whether or not the user having the above is determined to be a "non-negative user". By learning these sample data, the generation unit 132 can generate a model by identifying the explanatory variables that contributed to the result that a certain user was determined to be a “negative user”. In other words, the generation unit 132 generates a model in which the weight value of the explanatory variable that contributed to the determination is large, so that when an action history having certain feature information is input, the user corresponding to the action history. It is possible to generate a model that accurately determines whether or not is a "negative user".

The generation unit 132 may generate a model using all kinds of information regarding the information that the determination unit 133 uses as the determination element, that is, the user information acquired by the acquisition unit 131. For example, the generation unit 132 uses the tendency of the user's search query, the site browsing history, the purchase history, and the like as the characteristic information of the user.

An example of the model generated by the generation unit 132 will be described below. The learning method for the model generated by the generation unit 132 is not limited to the following examples, and various known machine learning methods may be adopted.

For example, the generation unit 132 generates an expression showing the relationship between an event indicating whether or not a user is a user determined to be a "negative user" and the behavior history of the user. Further, the generation unit 132 calculates what kind of weight each feature information in the user's action history has with respect to the determination result. As a result, the generation unit 132 can obtain information such as how much various feature information included in the user's action history contributes to the event that a certain user is determined to be a "negative user". For example, the generation unit 132 creates the following equation (1).

y (U01) = ω1 ・ x1 ＋ ω2 ・ x2 ＋ ω3 ・ x3 ・ ・ ・ ＋ ωN ・ xN ・ ・ ・ (1) (N is an arbitrary number)

The above equation (1) is, for example, an equation created for the user U01. In the above equation (1), "y (U01)" indicates whether or not the user U01 is determined to be a "negative user". For example, "y (U01)" is entered as "1" when the user U01 is determined to be a "negative user", and "0" when the user U01 is determined to be a "non-negative user". Is entered. In the embodiment, as shown in FIG. 4, since the user U01 is determined to be a "negative user", "y (U01)" takes a value of "1".

Further, in the above equation (1), "x" corresponds to each explanatory variable included in the action history of the user U01. For example, the explanatory variables "x1, x2, x3, ..., XN" in the above formula (1) correspond to the transmission history of search queries, the browsing history of websites, the purchase history on the Internet, and the like. .. For example, from the behavior history of user U01, the user U01 frequently browses the page of promotion of new subscription in financial services, does not use the contracted card at the time of purchase, and only the points given. If a certain tendency can be found, such as purchasing by using it or frequently searching service sites to which points are given, such information will greatly contribute as an explanatory variable. That is, the right side of the above equation (1) corresponds to the feature information included in the action history of the user U01.

In the above equation (1), "ω" is a coefficient of "x" and indicates a predetermined weight value. Specifically, "ω1" is a weight value of "x1", "ω2" is a weight value of "x2", and "ω3" is a weight value of "x3". As described above, the above equation (1) is a combination of the explanatory variable “x” corresponding to the feature information included in the action history and the variable (for example, “ω1 · x1”) including the predetermined weight value “ω”. Is created by

For example, in the above formula (1), "x1" corresponds to "search query transmission history", "x2" corresponds to "website browsing history", and "x3" corresponds to "purchase on the network". It is assumed that it is an explanatory variable corresponding to "history". In this case, the above equation (1) corresponding to the user U01 can be expressed as the following equation (2).

y (A01, U01) (= 1) = ω1 ・ (Search query transmission history) ＋ ω2 ・ (Website browsing history) ＋ ω3 ・ (Purchase history on the network) ＋ ωN ・ xN ・ ・ ・ (2)

Using an equation like the above equation (2), the generation unit 132 creates a relational expression between the judgment result and the action history not only in the user U01 but also in a number of samples that give a certain reliability to the model. .. Then, the weight value is calculated by regression analysis of these relational expressions, and a model showing the relation between the judgment result and the user's behavior history is generated. For example, after the above learning, if the weight value related to the transmission history of the search query is larger than that of other explanatory variables, the transmission history of the search query is compared with the browsing history of the website or the purchase history on the network. Therefore, an event indicating whether or not a certain user is a user determined to be a "negative user" is determined.

The generation unit 132 generates a model by using various known methods such as normalizing the user's behavior history and inputting it as an index value so that it can be substituted into the formula for model generation. May be good.

Further, in the above example, in order to simplify the explanation, rough information such as "transmission history of search query" is shown, but in reality, a weight value may be calculated for each of various queries. By such processing, for example, a user who has sent a search query such as "bonus point + insurance estimate" or "bonus point + credit card" in the past is a user who tends to be easily determined as a "negative user". As described above, a model that can grasp the influence of the user's behavior on the judgment result in more detail is generated.

The generation unit 132 may generate a model based on the user's attribute information together with the user's action history. As a result, the generation unit 132 can generate a model capable of determining not only users having similar behavior histories but also users who may become negative users according to the similarity and tendency of attribute information. ..

The generation unit 132 registers the generated model in the model storage unit 124. Further, the generation unit 132 may update the model at any time when the acquisition unit 131 acquires new user information after the model is generated.

(About judgment unit 133)
The determination unit 133 determines the creditworthiness of the user who newly tries to use the predetermined financial service based on the action history acquired by the acquisition unit 131. Specifically, the determination unit 133 determines the creditworthiness of a user who newly intends to use a predetermined financial service by using the model generated by the generation unit 132. For example, the determination unit 133 determines how credible the user is in a predetermined financial service based on the index value (for example, the matching rate with the positive example) output from the model, and determines the creditworthiness of the user. Can be determined.

The determination unit 133 may determine the creditworthiness of the user and may determine the service content when the user uses a predetermined financial service according to the determined creditworthiness. For example, the determination unit 133 determines, as the service content when the user uses the predetermined financial service, a privilege when the user subscribes to the predetermined financial service, an interest rate when the user uses the predetermined financial service, or Determine the content of at least one of the loan amount or the limit amount when the user uses the predetermined financial service.

Specifically, as shown in FIG. 8, the determination unit 133 determines the point award rate, which is a privilege when the user subscribes to a predetermined financial service, according to the determined credit rating (match rate). To do. Alternatively, the determination unit 133 may use the determination unit 133 according to the determined credit rating (match rate), for example, when the user uses a credit card contract or a financial service for receiving a car or housing loan. The interest rate, loan amount, credit card usage limit, etc. may be determined.

(About decision unit 134)
The determination unit 134 determines the information to be notified to the user terminal 10 based on the determination result by the determination unit 133. For example, the determination unit 134 determines that the determination unit 133 notifies the user terminal 10 of the condition regarding the predetermined service when the determination unit 133 determines the condition.

In addition, the determination unit 134 determines the mode of the information to be notified. For example, when the determination unit 134 notifies the service page on which the user applies for subscription of the determination result, the determination unit 134 determines the mode so as to notify the determination result by a banner advertisement or a pop-up display.

(About transmitter 135)
The transmission unit 135 transmits the notification content determined by the determination unit 134 to the user terminal 10. For example, in the transmission unit 135, if the user terminal 10 displays a web page and the web page is a page related to an application for a financial service, the display pops up on the page and provides a financial service to the user. Send a notification in a manner that displays the conditions at the time of subscription.

Note that the transmission unit 135 may transmit the notification via a predetermined transmission server without directly transmitting the notification from the determination device 100 to the user terminal 10. In this case, the transmission unit 135 causes the user terminal 10 to execute the transmission of the notification by controlling the predetermined transmission server.

Further, the transmission unit 135 may transmit the notification corresponding to various types such as a banner advertisement of a web page, an e-mail advertisement, a push notification, and a recommendation displayed on the web page.

[4. Processing procedure according to the embodiment]
Next, the procedure of processing by the determination device 100 according to the embodiment will be described with reference to FIGS. 9 and 10. First, the procedure of the generation process according to the embodiment will be described with reference to FIG. FIG. 9 is a flowchart (1) showing a processing procedure according to the embodiment.

As shown in FIG. 9, the acquisition unit 131 determines whether or not the user information has been acquired from the user terminal 10 (step 101). If the user information has not been acquired (step S101; No), the acquisition unit 131 waits until it is acquired.

On the other hand, when the user information is acquired (step S101; Yes), on the other hand, when the terminal information is acquired (step S101; Yes), the acquisition unit 131 stores the acquired user information in the user information storage unit 121 and stores it. (Step S102).

Then, the generation unit 132 determines whether or not a sufficient amount of data has been accumulated for model generation (step S103). For example, the generator 132 is of a sufficient amount (that is, a number that is considered statistically significant, for example, a number that satisfies 1% of the determination targets) to give a certain degree of reliability to the output result of the model. Determine if user information has been accumulated. Then, when a sufficient amount of data is not accumulated (step S103; No), the acquisition unit 131 continues the process of acquiring the user information (step S101).

On the other hand, when a sufficient amount of data is accumulated (step S103; Yes), the generation unit 132 generates a model based on the acquired user information (step S104). Then, the generation unit 132 registers the generated model in the model storage unit 124 (step S105).

Next, the procedure of the determination process according to the embodiment will be described with reference to FIG. FIG. 10 is a flowchart (2) showing a processing procedure according to the embodiment.

As shown in FIG. 10, the acquisition unit 131 determines whether or not new user information has been acquired from the user terminal 10 (step S201). If the user information has not been acquired (step S201; No), the acquisition unit 131 waits until it is acquired.

On the other hand, when the user information is acquired (step S201; Yes), the determination unit 133 inputs the user information into the model generated by the generation unit 132 (step S202). Then, the determination unit 133 determines the creditworthiness of the user (step S203).

Subsequently, the determination unit 134 determines the condition to be transmitted to the user terminal 10 based on the result determined by the determination unit 133, which is a condition according to the credit rating (step S204). The transmission unit 135 transmits a notification regarding the determined condition to the user terminal 10 (step S205).

[5. Modification example]
The determination device 100 described above may be implemented in various different forms other than the above embodiment. Therefore, a modified example of the embodiment will be described below.

[5-1. Judgment of user acquisition cost]
In the above embodiment, an example is shown in which the determination device 100 determines the creditworthiness when a user newly subscribes to a financial service. Here, the determination device 100 may determine not only the conditions for a user to newly subscribe to a financial service, but also the creditworthiness and conditions in other situations such as advertising activities for acquiring a new user. Good.

That is, the determination device 100 may determine the creditworthiness of the user and may determine the cost to promote the predetermined financial service to the user according to the determined creditworthiness.

For example, in a certain financial service, it is assumed that the cost per user is fixed for advertising expenses such as banner advertisements that encourage subscription to the service. Here, the determination device 100 determines the creditworthiness of each user for the user whose content such as an advertisement is to be determined. Then, the determination device 100 may newly determine the cost to be incurred per user according to the determined credit rating.

That is, for financial services, it is desirable to minimize costs such as advertising expenses for users who will become negative users in the future. Therefore, the determination device 100 suppresses costs such as advertising costs for users with low creditworthiness, and advertising costs for users with high creditworthiness (for example, users who have a strong tendency to behave differently from negative users). Make adjustments such as multiplying costs such as other users. As a result, the determination device 100 can improve the cost-effectiveness in advertising.

Further, in this case, the determination device 100 may not generate a model with a negative user as a positive example, but may generate a model with a positive user who is a user having a particularly high contribution to the service as a positive example. Then, the determination device 100 may make adjustments so as to spend a larger amount of advertising expenses on the user having a high matching rate with the positive user than other users.

[5-2. Content distribution]
The determination device 100 may distribute a predetermined content according to the determined credit rating. For example, the determination device 100 may deliver to the user terminal 10 an advertisement indicating that the privilege at the time of subscription is given preferential treatment, a recommendation for recommending subscription to a financial service, or the like, depending on the creditworthiness of the user.

[5-3. Use of user information]
In the above embodiment, it has been described that the determination device 100 uses information related to the user's search query, browsing history on the network, purchase history, and the like as the user's characteristic information. Here, the determination device 100 may determine the creditworthiness of the user by using any information as long as it is information indicating the characteristics of the user. In other words, the determination device 100 may generate a model using information that can represent the characteristics of the user.

For example, the determination device 100 may acquire information about the SNS used by the user. Specifically, the determination device 100 uses the content of a relatively new article posted on the SNS by the user (for example, the content of the article displayed on the so-called timeline), the number of images posted on the SNS by the user, and on the SNS. At least one of the number of related users (for example, the number of friends) is acquired in.

More specifically, the determination device 100 acquires the tendency of words included in the text data of the article posted to the SNS by the user. As a result, the determination device 100 acquires information about an event that the user is interested in. Alternatively, the determination device 100 determines the number of images posted on the SNS, the content of the images, the number of users having a relationship on the SNS, that is, the number of users having a connection on the SNS (for example, the number of friends and the number of followers). get. As a result, the determination device 100 acquires information indicating what kind of daily life the user is living.

Then, the determination device 100 generates a model including the acquired information on the SNS, and determines the creditworthiness of the user based on the generated model. As described above, since the determination device 100 can determine the credit rating based on various information indicating the characteristics of the user, the determination process can be performed from various viewpoints.

[5-4. Image recognition]
Further, the determination device 100 may perform processing as information on the SNS based not only on the number of images posted by the user but also on the content indicated by the images by image recognition or the like.

For example, the determination device 100 may determine which user has the same tendency as the negative user based on the content itself of the image posted by the user. For example, in the determination device 100, among the images uploaded to the SNS by the user, what kind of daily life the user spends based on the person, landscape, content, genre, category, image quality, etc. in the image. The image may be extracted as feature information, and a model may be generated using the extracted information as feature information. As a result, the determination device 100 can determine the credit rating based on various information indicating the characteristics of the user, so that the determination process can be performed from various viewpoints.

[6. Others]
Further, among the processes described in the above-described embodiment, all or a part of the processes described as being automatically performed can be manually performed, or the processes described as being manually performed can be performed. All or part of it can be done automatically by a known method. In addition, the processing procedure, specific name, and information including various data and parameters shown in the above document and drawings can be arbitrarily changed unless otherwise specified. For example, the various information shown in each figure is not limited to the illustrated information.

Further, each component of each of the illustrated devices is a functional concept, and does not necessarily have to be physically configured as shown in the figure. That is, the specific form of distribution / integration of each device is not limited to the one shown in the figure, and all or part of them may be functionally or physically distributed / physically in arbitrary units according to various loads and usage conditions. It can be integrated and configured. For example, the determination unit 133 shown in FIG. 3 and the determination unit 134 may be integrated. Further, for example, the information stored in the storage unit 120 may be stored in an externally provided storage device via the network N.

Further, for example, in the above embodiment, an example is shown in which the determination device 100 performs an acquisition process for acquiring user information of the user terminal 10 and a determination process for estimating the creditworthiness. However, the above-mentioned determination device 100 may be separated into an acquisition device that performs acquisition processing and a determination device that performs determination processing. In this case, the acquisition device has at least the acquisition unit 131. The determination device has at least a determination unit 133. In this case, the processing by the determination device 100 according to the embodiment is realized by the determination system 1 including the acquisition device and each device such as the determination device.

In addition, the above-described embodiments and modifications can be appropriately combined as long as the processing contents do not contradict each other.

[7. Hardware configuration]
The determination device 100 and the user terminal 10 according to the above-described embodiment are realized by, for example, a computer 1000 having a configuration as shown in FIG. Hereinafter, the determination device 100 will be described as an example. FIG. 11 is a hardware configuration diagram showing an example of a computer 1000 that realizes the function of the determination device 100. The computer 1000 has a CPU 1100, a RAM 1200, a ROM 1300, an HDD 1400, a communication interface (I / F) 1500, an input / output interface (I / F) 1600, and a media interface (I / F) 1700.

The CPU 1100 operates based on a program stored in the ROM 1300 or the HDD 1400, and controls each part. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 is started, a program that depends on the hardware of the computer 1000, and the like.

The HDD 1400 stores a program executed by the CPU 1100, data used by such a program, and the like. The communication interface 1500 receives data from another device via the communication network 500 (corresponding to the network N shown in FIG. 2) and sends the data to the CPU 1100, and the data generated by the CPU 1100 is transmitted to the other device via the communication network 500. Send to the device.

The CPU 1100 controls an output device such as a display or a printer, and an input device such as a keyboard or a mouse via the input / output interface 1600. The CPU 1100 acquires data from the input device via the input / output interface 1600. Further, the CPU 1100 outputs the data generated via the input / output interface 1600 to the output device.

The media interface 1700 reads a program or data stored in the recording medium 1800 and provides the program or data to the CPU 1100 via the RAM 1200. The CPU 1100 loads the program from the recording medium 1800 onto the RAM 1200 via the media interface 1700, and executes the loaded program. The recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or PD (Phase change rewritable Disk), a magneto-optical recording medium such as MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory. And so on.

For example, when the computer 1000 functions as the determination device 100 according to the embodiment, the CPU 1100 of the computer 1000 realizes the function of the control unit 130 by executing the program loaded on the RAM 1200. Further, the data in the storage unit 120 is stored in the HDD 1400. The CPU 1100 of the computer 1000 reads and executes these programs from the recording medium 1800, but as another example, these programs may be acquired from another device via the communication network 500.

[8. effect〕
As described above, the determination device 100 according to the embodiment includes the acquisition unit 131 and the determination unit 133. The acquisition unit 131 acquires the action history on the user's network. The determination unit 133 determines the creditworthiness of the user who newly tries to use the predetermined financial service based on the action history acquired by the acquisition unit 131.

As described above, the determination device 100 according to the embodiment determines the creditworthiness of the user regarding the financial service by using the user's action history as a determination element. That is, the determination device 100 captures the characteristics of the user based on the behavior history of the user on the network, and determines whether or not the user is a good user for a predetermined financial service. As a result, the determination device 100 can measure the degree of contribution of the user to the service in the future without obtaining a concrete result (for example, how much the user will use the service) before using the service. Therefore, it is possible to appropriately judge the creditworthiness of an individual in a financial service.

Further, the determination device 100 according to the embodiment generates a model for examining a user who uses a predetermined financial service based on the action history acquired by the acquisition unit 131. The determination unit 133 determines the creditworthiness of a user who newly intends to use a predetermined financial service by using the model generated by the generation unit 132.

In this way, the determination device 100 according to the embodiment generates a user model used for the determination process, and determines the user by using the generated model. As a result, the determination device 100 can improve the processing efficiency and the accuracy of the determination processing.

In addition, the acquisition unit 131 has at least one of information on a search query sent by the user to the search service, browsing history of the user's predetermined service page, or user's purchasing history in the predetermined service as an action history on the network. Get one. The generation unit 132 generates a model based on at least one of the information about the search query sent by the user to the search service, the browsing history of the user's predetermined service page, or the user's purchase history in the predetermined service. To do.

As described above, the determination device 100 according to the embodiment performs the determination process using the information regarding the search query and the like transmitted by the user. As described above, the search query, browsing history, action history, etc. sent by the user can be said to specifically express the user's interests. By using such information in the determination process, the determination device 100 can more accurately capture the tendency of the user.

Further, the generation unit 132 generates a model based on the behavior history of a user who has a contract for a predetermined financial service and whose utilization rate of the predetermined financial service is lower than a predetermined threshold value.

As described above, the determination device 100 according to the embodiment generates a model with a user whose service utilization rate is lower than a predetermined threshold value, that is, a so-called negative user, as a positive example or a negative example in the actually operating financial service. It may be. As a result, the determination device 100 can generate a model capable of accurately determining a user who does not contribute to the service.

In addition, the generation unit 132 generates a model related to a financial service having a system for giving a predetermined point to a user among the predetermined financial services.

In this way, the determination device 100 according to the embodiment generates a model for determining a user in a service having a point system. In general, when there is a virtual currency system such as a point system, negative users who only intend to use the virtual currency are likely to occur. The determination device 100 can eliminate negative users and operate an appropriate service by generating a model capable of extracting negative users in such a system.

In addition, the generation unit 132 generates a model for a financial service having a system in which predetermined points are given to the user when the service is subscribed.

As described above, the determination device 100 according to the embodiment generates a model for determining a user in a service having a point awarding system as a privilege at the time of subscription. In general, in services that have benefits at the time of subscription, negative users who only aim for the benefits are likely to occur. The determination device 100 can eliminate negative users and operate an appropriate service by generating a model capable of extracting negative users in such a system.

In addition, the acquisition unit 131 further acquires the attribute information of the user who has acquired the action history. The generation unit 132 generates a model based on the attribute information of the user.

As described above, the determination device 100 according to the embodiment may perform the generation process using not only the user's action history but also the similarity of the user's attribute information. As a result, the determination device 100 can improve the accuracy of the determination process.

In addition, the acquisition unit 131 acquires information on the SNS (Social Networking Service) used by the user as an action history on the network. The generation unit 132 generates a model based on the information about the SNS used by the user.

As described above, the determination device 100 according to the embodiment may generate a model by using the information about the SNS used by the user. Since the results of the user's interests and actions in daily life are uploaded to the SNS as a record, the information held in the SNS can be information indicating the characteristics of the user. By using such information indicating the characteristics of the user in the model generation, the determination device 100 can improve the accuracy of the process of determining the creditworthiness of the user.

In addition, the determination unit 133 determines the creditworthiness of the user, and also determines the service content when the user uses a predetermined financial service according to the creditworthiness.

In this way, the determination device 100 according to the embodiment may determine the service content (condition) according to the credit rating. As a result, the determination device 100 can take flexible measures such as accepting subscription according to various conditions even for a user who may become a negative user.

In addition, the determination unit 133 includes, as the service content when using the predetermined financial service, a privilege when the user subscribes to the predetermined financial service, an interest rate when the user uses the predetermined financial service, or a predetermined financial service. Determine the content of at least one of the loan amount or limit when the user uses the financial service.

As described above, the determination device 100 according to the embodiment may determine the service content (condition) according to the credit rating in more detail. As a result, the determination device 100 sets slightly strict conditions for users who may become negative users until a certain degree of credit is obtained, while preferential conditions are given to users who have credit. You can take flexible measures such as presenting.

In addition, the determination unit 133 determines the creditworthiness of the user, and also determines the cost of promoting the predetermined financial service to the user according to the creditworthiness.

As described above, the determination device 100 according to the embodiment may perform processing such as adjusting the advertising cost according to the creditworthiness of the user. As a result, the determination device 100 can improve the cost-effectiveness because an appropriate cost can be applied to the acquisition of the user who brings a profit when the acquisition is made.

The determination device 100 according to the embodiment may function as a generation device that performs model generation processing. In this case, the generation device has at least an acquisition unit 131 and a generation unit 132. The acquisition unit 131 acquires the action history on the user's network. The generation unit 132 generates a model for examining a user who uses a predetermined financial service based on the action history acquired by the acquisition unit 131.

In this way, the generator makes it possible to examine a user who uses a predetermined financial service by modeling the user based on the user's behavior history. For example, according to the generation device, it is possible to generate a model capable of estimating what kind of behavior history a user has for a service. As a result, the generator can appropriately determine the creditworthiness of an individual in a financial service.

Although some of the embodiments of the present application have been described in detail with reference to the drawings, these are examples, and various modifications are made based on the knowledge of those skilled in the art, including the embodiments described in the disclosure column of the invention. It is possible to practice the present invention in other improved forms.

Further, the above-mentioned "section, module, unit" can be read as "means" or "circuit". For example, the acquisition unit can be read as an acquisition means or an acquisition circuit.

1 Judgment system 10 User terminal 30 Web server 100 Judgment device 110 Communication unit 120 Storage unit 121 User information storage unit 122 Attribute information table 123 Action information table 124 Model storage unit 125 Condition information storage unit 130 Control unit 131 Acquisition unit 132 Generation unit 133 Judgment unit 134 Decision unit 135 Transmission unit

Claims (11)

The behavior history on the network of the first user who is a user who has a contract for a predetermined financial service and the usage rate of the predetermined financial service is lower than the predetermined threshold, and the contract for the predetermined financial service. an acquisition unit for acquiring the action history on the second user's network is the user is not,
A generation unit that generates a model for examining a second user who intends to use the predetermined financial service based on the behavior history of the first user acquired by the acquisition unit.
Using the model generated by the generating unit, by entering into the model as input information the action history of the second user acquired by the acquiring unit, the second to be utilizing the predetermined financial services A determination unit that determines the creditworthiness of whether or not the user is a user whose usage rate of the predetermined financial service is higher than the predetermined threshold value .
Judgment device characterized by being equipped with. The acquisition unit
As the action history on the network, the information about the search query sent by the first user to the search service, the browsing history of the predetermined service page of the first user, or the purchase history of the first user in the predetermined service. Get at least one and
The generator
Based on at least one of the information about the search query sent by the first user to the search service, the browsing history of the predetermined service page of the first user, or the purchase history of the first user in the predetermined service. , Generate the model,
The determination device according to claim 1 , wherein the determination device is characterized by the above. The generator
A model for a financial service having a system for giving a predetermined point to the second user among the predetermined financial services is generated.
The determination device according to claim 1 or 2 , wherein the determination device is characterized by the above. The generator
Generate a model for the financial service having a system in which predetermined points are given to the second user when the service is subscribed.
The determination device according to claim 3 , wherein the determination device is characterized by the above. The acquisition unit
Further acquire the attribute information of the first user who acquired the action history,
The generator
Generate the model based on the attribute information of the first user.
The determination device according to any one of claims 1 to 4 , wherein the determination device is characterized in that. The acquisition unit
As the action history on the network, information on the SNS (Social Networking Service) used by the first user is acquired, and information is obtained.
The generator
The model is generated based on the information about the SNS used by the first user.
The determination device according to any one of claims 1 to 5 , wherein the determination device is characterized in that. The determination unit
The creditworthiness of the second user is determined, and the service content when the second user uses the predetermined financial service is determined according to the creditworthiness.
The determination device according to any one of claims 1 to 6 , characterized in that. The determination unit
As the service content when using the predetermined financial service, the privilege when the second user subscribes to the predetermined financial service, the interest rate when the second user uses the predetermined financial service, or Judging the content regarding at least one of the loan amount or the limit amount when the second user uses the predetermined financial service.
The determination device according to claim 7 , wherein the determination device is characterized by the above. The determination unit
The creditworthiness of the second user is determined, and the cost of promoting the predetermined financial service to the second user is determined according to the creditworthiness.
The determination device according to any one of claims 1 to 8 , wherein the determination device is characterized by the above. It is a judgment method executed by a computer.
The behavior history on the network of the first user who is a user who has a contract for a predetermined financial service and the usage rate of the predetermined financial service is lower than the predetermined threshold, and the contract for the predetermined financial service. an acquisition step of acquiring the action history on the second user's network is the user is not,
A generation process for generating a model for examining a second user who intends to use the predetermined financial service based on the behavior history of the first user acquired by the acquisition process, and a generation process.
Using the model generated by the generating step, by entering into the model of the second user action history acquired by the acquisition step as the input information, the second to be utilizing the predetermined financial services A determination step for determining the creditworthiness of a user as to whether or not the user is a user whose usage rate of the predetermined financial service is higher than a predetermined threshold .
A determination method characterized by including. The behavior history on the network of the first user who is a user who has a contract for a predetermined financial service and the usage rate of the predetermined financial service is lower than the predetermined threshold, and the contract for the predetermined financial service. an acquisition procedure for acquiring the action history on the second user's network is the user is not,
A generation procedure for generating a model for examining a second user who intends to use the predetermined financial service based on the behavior history of the first user acquired by the acquisition procedure, and a generation procedure.
Using the model generated by the generation step, by entering into the model of the second user action history acquired by the acquisition procedure as the input information, the second to be utilizing the predetermined financial services A determination procedure for determining the creditworthiness of a user as to whether or not the user is a user whose usage rate of the predetermined financial service is higher than the predetermined threshold value .
A judgment program characterized by having a computer execute.

Images