JP7173507B2 - Sales support device, sales support method and program - Google Patents

Description

The present invention relates to a sales support device, a sales support method, and a program.

In recent years, financial institutions have begun to pay attention to EBM (event-based marketing) that proposes financial products required by customers at appropriate timing. EBM detects customer (target) attribute information and changes in transaction behavior from the customer database, predicts this as an event that triggers the occurrence of financial needs, and proposes financial products that customers want. It is a marketing method.

Conventionally, as a method similar to EBM, extraction conditions such as arbitrarily set thresholds for statistics such as customer attribute information that is relatively static and difficult to change, balance of deposit assets, past financial purchase history, etc. As a method of discovering prospective customers has been adopted. For example, customers with a deposit amount of 10 million yen or more are extracted as a quantitative threshold for the deposit amount, and sales approaches such as investment trust products are made to the extracted prospective customers. However, even if the deposit amount is less than 10 million yen, there are customers who have strong needs, so customers who have latent needs will still be missed. In addition, since the customer group does not change much, it is difficult to grasp the changes in customer needs appropriately from day to day, which makes it difficult to accurately extract potential customers.

As a technology related to EBM of financial institutions, for example, in Patent Document 1, a company that is different from the current company-specific information registered this time and the previous company-specific information registered before the current company-specific information is a target company. A trading company development support method for supporting sales activities by extracting and distributing information about the target company to a person in charge is described.

In addition, for example, in Patent Document 2, based on the past transfer history, there is no main account that has received a predetermined continuous transfer or is making a predetermined continuous transfer, and there is no predetermined continuous transfer. a means for classifying large deposits into sub-accounts; a means for determining that large deposits deposited into the main account are deposits with a predetermined purpose based on the attribute data of the main account; means for determining that a deposit is a candidate deposit that may be a deposit with a predetermined purpose; means for judging that a deposit candidate deposited in a sub-account is a deposit for the same purpose as a large deposit deposited in the main account, based on the attribute data of the sub-account when the date matches the date. is described.

Further, for example, in Patent Document 3, a corporation extracting means of a corporation sales support system extracts corporations to be operated from corporations related to each settlement indicated by corporation settlement information indicating settlements made between corporations. The method for extracting companies consists of the combination of the receiving company and the receiving company for each payment made within the target period, and the receiving company and receiving company for each payment made within the past period prior to the relevant target period. At least one of a corporation that has received money from a new customer within the target period and a corporation that has received money from the new customer within the target period is extracted based on the combination of the corporations on the receiving side. The sales support information output means is a corporate sales support system that, when a corporation is extracted by the corporation extraction means, outputs sales support information for supporting sales to the extracted corporation.

Japanese Patent No. 6208907 Japanese Patent No. 5850592 Japanese Patent No. 5416852

The inventions described in Patent Documents 1 to 3 above focus on changes in customer information held by financial institutions (for example, company-specific information, balances of main and sub-accounts, and corporate payment information), and based on assumed needs A certain rule is defined as an extraction condition, and when a change in customer information that meets the rule is detected from the customer database, the customer is extracted as a target customer.

However, the conditions for extracting target customers are generalized rules determined in advance by the system administrator based on assumed needs. For this reason, needless to say, it is impossible to extract target customers who are expected to have high needs even though they do not apply to the rule. That is, the lifestyles of customers have become more and more diversified in recent years, and it is difficult to finely discover potential prospective customers only by using generalized rules for changes in customer characteristics.

SUMMARY OF THE INVENTION The present invention has been proposed in view of the above points. In one aspect, it is an object of the present invention to accurately extract customers who are expected to have a need for a predetermined financial product, and to support efficient sales activities in financial institutions. and

In order to solve the above problems, a sales support device according to the present invention is a sales support device for a financial institution, comprising acquisition means for acquiring transaction data of customers in the financial institution, and a relationship determining means for determining a relationship between the customer's first transaction data and the customer's second transaction data at a current time; and the relationship determining means for determining that the first transaction data and the second transaction data are related. and an output means for outputting the customers extracted by the extraction means.

Further, in order to solve the above problems, a sales support device according to the present invention is a sales support device for a financial institution, which acquires at least two or more different types of transaction data of customers in the financial institution. a relationship determining means for determining the relationship between the customer's first transaction data pattern at the time of purchase of financial products in the past and the customer's second transaction data pattern at the present time; and the relationship determination An extraction means for extracting the customer determined by the means that the pattern of the first transaction data and the pattern of the second transaction data are related, and an output means for outputting the customer extracted by the extraction means.

According to the embodiment of the present invention, in one aspect, it is possible to accurately extract customers who are expected to have needs for a predetermined financial product, and to support efficient sales activities in financial institutions.

It is a figure which shows the structural example of the sales support system which concerns on this embodiment. It is a figure which shows the hardware structural example of the management server which concerns on this embodiment. It is a figure which shows the software structural example of the management server which concerns on this embodiment. An example of customer information held by a financial institution system 10 (for example, a core system that manages various deposits such as ordinary deposits and time deposits) is shown. An example of balance information held by a financial institution system 10 (for example, a core system that manages various deposits such as ordinary deposits and time deposits) is shown. An example of transaction statement information possessed by a financial institution system 10 (for example, a core system that manages various deposits such as ordinary deposits and time deposits) is shown. An example of investment trust information held by a financial institution system 10 (a sales management system that manages sales results of financial products such as investment trusts) is shown. An example of asset management policy information possessed by the financial institution system 10 (front compliance system for managing and proposing financial products according to the asset management needs of each customer) is shown. An example of negotiation history information possessed by the financial institution system 10 (history system for managing negotiation histories) is shown. It is a flow chart which shows prospective customer extraction processing concerning this embodiment. The pattern distribution of each transaction data at the date and time of investment trust purchases in the past is shown. FIG. 4 shows a diagram for explaining the relationship between pattern distributions of transaction data; FIG. 4 shows a diagram for explaining the relationship between pattern distributions of transaction data; FIG. 10 is a diagram for explaining the relation of index pattern distribution based on each transaction data; FIG. 1 shows an example of a sales destination priority list according to the present embodiment; An example of a sales product priority list (modification) according to the present embodiment is shown. FIG. 4 shows a diagram for explaining the relationship between pattern distributions of transaction data;

An embodiment of the present invention will be described in detail with reference to the drawings.

<System configuration>
FIG. 1 is a diagram showing a configuration example of a sales support system according to this embodiment. The sales support system 100 of FIG. 1 includes a financial institution system 10, a sales promotion support system 20, a management server 30, a processing DB 40, and a sales terminal 50, which are connected via a network 70.

The financial institution system 10 includes various systems and DBs (databases) owned by financial institutions such as banks. Financial institution systems include, for example, a core system that manages various deposits such as ordinary deposits and time deposits, a sales management system that manages sales performance of financial products, and a system that manages and proposes financial products that meet the asset management needs of each customer. It includes a front compliance system for management, a history system (CRM) that manages negotiation history, and various DBs associated with each system. Examples of types of financial products include investment trusts, free loans, card loans, car loans, and educational loans.

The sales promotion support system 20 is a system for assisting and supporting the sales activities of sales personnel in financial institutions. For example, it manages the customer destinations of sales representatives, and manages the progress of sales such as daily sales reports. In addition, on the system, it is possible to share information and exchange opinions among the persons in charge, and to report information to superiors and exchange instructions.

Based on the processed data in the processing DB 40, the management server 30 extracts prospective customers who are predicted to have a high possibility of purchasing financial products (for example, investment trust products) together with their priorities (high order of purchase possibility). It is a server device that The management server 30 also creates (generates) a business destination priority list to be used by the sales representative based on the priority.

Furthermore, when the results of the sales activities conducted by the salesperson based on the sales destination priority list are fed back to the sales promotion support system 20, the management server 30 sends the sales destination priority list (prediction list) and the feedback Verifies the accuracy of the forecast by comparing it with the results obtained, and reflects it in the preparation of the next customer priority list.

The processing DB 40 sequentially acquires raw data (referred to as such because it has not been processed) from the DB of the financial institution system 10 in operation by the financial institution, and converts the acquired raw data into a format that can be calculated by the management server 30. This is a DB storing processed data. Machine learning methods often cannot handle raw input data such as text and time-series data as they are, so such unstructured data is converted into vectors through conversion processing. Although there is a difference in format between raw data and processed data, the content and meaning of the data are the same.

The sales terminal 50 is, for example, a PC (personal computer), a smart phone, a tablet terminal, or the like, and is a user terminal used by a sales representative at a sales office or on the go. The salesperson accesses the management server 10 using the sales terminal 50, acquires and displays the sales destination priority list. As described above, the sales destination priority list is a list of prospective customers who are predicted to be highly likely to purchase a predetermined financial product (for example, investment trust products) in order of priority. By approaching customers (targets) on the priority list of sales destinations in order of priority, the sales staff can carry out efficient sales activities even within a limited amount of time. The business terminal 50 is preinstalled with a predetermined application program, web browser, or the like for acquiring and displaying the business destination priority list from the management server 30 .

The network 70 is a communication network including wired and wireless. The network 70 includes, for example, the Internet, a public line network, WiFi (registered trademark), and the like.

<Hardware configuration>
FIG. 2 is a diagram showing a hardware configuration example of a management server according to this embodiment. As shown in FIG. 2, the management server 30 includes a CPU (Central Processing Unit) 31, a ROM (Read Only Memory) 32, a RAM (Random Access Memory) 33, a HDD (Hard Disk Drive) 34, and a communication device 35. have.

The CPU 31 executes various programs and performs arithmetic processing. The ROM 32 stores programs necessary for activation. The RAM 33 is a work area for temporarily storing processing by the CPU 11 and storing data. The HDD 34 stores various data and programs. The communication device 35 communicates with other devices via the network 70 .

<Software configuration>
FIG. 3 is a diagram showing a software configuration example of a management server according to this embodiment. The management server 30 has a data acquisition unit 301, a feature amount calculation unit 302, a relation determination unit 303, an extraction unit 304, a sales destination list creation unit 305, and an output unit 306 as main functional units.

The data acquisition unit 301 acquires customer information and transaction data of customers in financial institutions from the processing DB 40 (or the sales promotion support system 20).

The feature quantity calculation unit 302 calculates a feature quantity (for example, a feature vector) of the transaction data from the customer's transaction data pattern.

The relationship determining unit 303 determines whether or not there is a relationship based on the degree of relationship between the customer's transaction data at the time of purchase of financial products in the past and the customer's current transaction data. For example, distance determination by feature vectorization can be used as one method for determining relationships between transaction data. Specifically, the distance between the feature vector calculated from the customer's transaction data pattern at the time the customer purchased financial products in the past and the feature vector calculated from the current (present) customer transaction data pattern (corresponding to the degree of relevance) is calculated, and based on whether or not the distance is close, it is determined whether or not the two transaction data are related.

The extracting unit 304 selects the customer determined by the relationship determination unit 303 as having a relationship between the customer's transaction data at the time of purchase of financial products in the past and the current transaction data of the customer as a customer to be a business partner. , along with information indicating the priority.

The customer list creation unit 305 creates customer list information in which the customers extracted by the extraction unit 304 are arranged in descending order of priority.

The output unit 306 outputs the sales destination list information to the sales terminal 50 .

Each functional unit is implemented by a computer program executed on hardware resources such as the CPU, ROM, and RAM of the computer that constitutes the management server 30 . These functional units may be read as "means", "module", "unit", or "circuit". Also, each DB may be arranged in the HDD 34 of the management server 30 or an external storage device on the network 70 . Moreover, each functional unit of the management server 30 may not only be implemented by a single server device, but may also be implemented as a system composed of a plurality of devices by distributing the functions.

(Data item example of DB of financial institution system)
Next, an example of data items in the DB (or processing DB 40) of the financial institution system 10 is shown. However, it goes without saying that the data items shown in FIG. 4 are only examples, and there may be other data items.

FIG. 4A shows an example of customer information held by the financial institution system 10 (for example, a core system that manages various deposits such as ordinary deposits and time deposits). This is customer attribute information for each customer, and is registered mainly based on the customer's application when opening an account. Depending on the type of customer, there are individual customers and corporate customers.

FIG. 4B shows an example of balance information held by the financial institution system 10 (for example, a core system that manages various deposits such as ordinary deposits and time deposits). For example, it is the balance information of each account held by each customer, such as an ordinary deposit account, a checking account, a fixed deposit account, a foreign currency deposit account, and an investment trust account. All past balances as well as current (latest) balances are recorded.

FIG. 4C shows an example of transaction statement information held by the financial institution system 10 (for example, a core system that manages various deposits such as ordinary deposits and time deposits). This is detailed information of each transaction that occurred for each customer, such as ordinary deposit transaction details, credit card usage details, current account transaction details, exchange transaction details, and the like. All transactions from the past to the present are recorded.

FIG. 4D shows an example of investment trust information held by the financial institution system 10 (a sales management system that manages sales results of financial products such as investment trusts). Information related to investment trusts for each customer, such as customer investment trust account information, deposit balance information, distribution redemption details information, and profit and loss information.

FIG. 4E shows an example of asset management policy information possessed by the financial institution system 10 (front compliance system for managing and proposing financial products that meet the asset management needs of each customer). It is the policy and asset management needs for each customer's financial asset management, and is registered mainly based on the customer's application when opening an investment trust account. Sales representatives will propose financial products and asset management that match the policy needs according to the policy.

FIG. 4F shows an example of negotiation history information held by the financial institution system 10 (history system for managing negotiation histories). A history of negotiations, proposals, or direct mail transmissions made by a salesperson or person in charge of a window at a financial institution is recorded for each customer. As a result, all past negotiation histories between customers and financial institutions are managed so that they can be browsed.

Here, the customer information and the asset management policy information are relatively static and hard to change information. On the other hand, balance information, transaction statement information, mutual fund information, and negotiation history information are relatively dynamic and changeable information, and are "transaction data." In general, transaction data is one of the types of data handled by corporate information systems, etc., and refers to data that records the details of events that occur in the course of business.

Transaction data according to the present embodiment refers to data that records details of events that occur with the use of financial services by customers, such as deposit balance information, transaction statement information, and investment trust information, particularly at financial institutions. . In addition, the transaction data according to the present embodiment is data with relatively frequent information changes (update frequency) on a daily basis compared to information such as customer information that does not change very frequently from the time of registration. However, since the update frequency depends on the frequency of use of financial services by each customer, the specific update frequency does not matter.

<Information processing>
Next, various information processing executed by the management server 30 will be described in detail.
(data update processing)
The management server 30 sequentially acquires raw data from the DB of the financial institution system 10 in operation by the financial institution, and processes and converts the raw data acquired by the management server 30 into a form in which the management server 30 can perform calculation processing. update to The update cycle is arbitrarily set according to the operation, for example, every second, every several seconds to several tens of seconds, every minute, every few minutes to several tens of minutes, every hour, every few hours, every day, every predetermined day, etc. Although it can be set, the shorter the update interval, the better, and it is desirable to update in real time together with the update of the raw data on the DB of the financial institution system 10 . As a result, in the processing DB 40, data equivalent to the DB of the financial institution system 10 is updated at each update interval although there is a difference in format between the raw data and the processed data.

(Preprocessing)
In this embodiment, an example of extracting prospective customers who are highly likely to purchase investment trust products as an example of financial products will be described.

First, the management server 30 classifies target customers into groups according to whether or not they have purchased investment trusts in the past, based on customer transaction data (especially investment trust information). Customers to be classified are existing customers of the financial institution and have at least an ordinary deposit account.
・Customer group A: Customers who have purchased investment trusts in the past and actually still hold investment trusts (additional buyer target for investment trusts), and customers who have purchased investment trusts in the past but currently do not Customers who do not hold investment trusts (repurchase targets for investment trusts)
・Customer group B: Customers who have only a savings account such as an ordinary savings account, have no experience of purchasing investment trusts in the past, and do not currently hold investment trusts (target for new purchasers of investment trusts)

(Prospect customer extraction processing for investment trusts)
Next, the process of judging and extracting prospective investment trust customers will be described. The extracted customer is listed as a business destination in the business destination priority list.

In the prospective customer extraction process for investment trusts, for customers classified into customer group A who have experience purchasing investment trusts in the past, a feature vector P representing the feature amount of transaction data at the time of past purchases of the customer himself/herself, A feature vector N indicating the feature amount of the current transaction data of the customer himself/herself is calculated, and based on the distance between the feature vector P and the feature vector N, whether or not the customer is currently likely to purchase investment trusts, and the degree of such possibility. judge.

On the other hand, for customers classified into customer group B who have no purchase experience of investment trusts in the past, a feature vector P′ representing the feature amount of transaction data at the time of past purchase of the customer classified into customer group A and the customer A feature vector N indicating the feature amount of transaction data at the current point in time is calculated for itself, and based on the distance between the feature vector P' and the feature vector N, whether or not the customer is currently likely to purchase an investment trust and whether or not determine the extent. A detailed description will be given below.

FIG. 5 is a flowchart showing prospective customer extraction processing according to the present embodiment. The operating subject is the management server 30 .

S1: The management server 30 acquires one candidate customer from the candidate customers to be extracted. A candidate customer is a predetermined customer segment. Customer segments that are candidate customers can be selected and set as follows. For example, all customers owned by the financial institution (e.g., customers who hold accounts), all customers owned by the branch (e.g., customers who hold accounts) in the case of a business branch, or a group of sales representatives If there is, it is all the customers that the salesperson is in charge of. Alternatively, customers who have an account with no purchase experience of investment trusts in the past (equivalent to customer group B above) and customers who have an account with investment trust purchases in the past (equivalent to customer group A above). You can tie it. Furthermore, it is also possible to set a specific number of customers out of all the customers of the financial institution. A determination is made as to whether or not each candidate customer is a prospective customer. Candidate customers may be arbitrarily determined by inputting detailed conditions (customer attribute information such as place of residence, age, occupation, income, etc.).

S2: The management server 30 determines whether or not the candidate customer acquired in S1 has purchased investment trusts in the past. If the candidate customer acquired in S1 has experience in purchasing investment trusts in the past, that is, if the candidate customer is classified into customer group A, the process proceeds to S3. On the other hand, if the candidate customer acquired in S1 has no purchase experience of investment trusts in the past, that is, if the candidate customer is classified into customer group B, the process proceeds to S21.

S3: The management server 30 acquires from the processing DB 40 the transaction data at the time when the candidate customer classified into the customer group A purchased an investment trust in the past (or for a predetermined period before the purchase corresponding to immediately before the purchase).

The transaction data to be acquired is not only one type of transaction data, but at least two types of transaction data at the time of purchase. As for which type of transaction data to acquire, it is possible to acquire all types of transaction data, but preferably appropriate types of transaction data are selectively acquired. Which type of transaction data to select Individually Although it depends on the target financial product, for example, historical analysis of transaction data of customers who purchased the target financial product It is also possible to make a selection based on whether or not the customer who received the investment finally purchased the investment trust, and to change or correct the selection.

Also, when the dates and times of purchase of a plurality of investment trusts are specified, the transaction data (transaction data values) at all the dates and times of purchase are acquired. Alternatively, when a plurality of investment trust purchase dates are specified, transaction data for any one date and time, such as the latest date and time, may be acquired.

S4: The management server 30 calculates a feature vector P from the plurality of transaction data patterns (a combination of a plurality of transaction data (values)) acquired in S3. The calculated feature vector P indicates the feature amount of the candidate customer's transaction data situation at the time when the candidate customer purchased the past investment trust. Note that if multiple investment trust purchase dates are specified and transaction data for multiple purchase dates are acquired, feature vectors P (P1, P2, P3, . . . ) for each purchase date and time are calculated. be able to.

FIG. 6 shows the pattern distribution of each transaction data on the date and time of investment trust purchases in the past. In the figure, A, B, C, D, and E are different types of transaction data items. The customer has a track record of purchasing investment trusts in the past at timings when each transaction data value has the pattern distribution shown in FIG. Therefore, the feature vector P is a numerical representation of a situation in which the customer's demand for investment trusts is expected to increase based on the pattern distribution (feature group) of past transaction data possessed by the financial institution.

S5: The management server 30 acquires the current transaction data of the candidate customer from the processing DB 40 this time. The transaction data at the current point in time is the transaction data last updated on the processing DB 40 . Also, the transaction data to be acquired is the same type of transaction data as corresponding to the transaction data acquired in S3. This is to match the types of transaction data to be compared.

S6: The management server 30 calculates a feature vector N from the transaction data pattern (combination of transaction data (values)) acquired in S5. The calculated feature vector N indicates the feature amount of the candidate customer's transaction data situation at the current time of the candidate customer.

S7: The management server 30 executes a relationship determination process between the feature vector P and the feature vector N. FIG. For customers classified into customer group A who have purchased investment trusts in the past, the feature vector P of the transaction data of the customer himself/herself at the time of past purchase and the feature vector N of the current transaction data of the customer himself/herself A distance (corresponding to the degree of association) is calculated, and the presence or absence of association is determined based on the calculated distance.

Specifically, the management server 30 first calculates the distance between the feature vector P and the feature vector N. FIG. Note that the distance between feature vectors can be calculated by a conventional method, but the shorter the distance between the calculated feature vectors, the higher (larger) the degree of relevance, and the longer the distance, the lower (smaller) the degree of relevance.

Next, it is determined whether the distance between the calculated feature vectors is smaller than a reference value (determines whether it is closer than the reference value). If it is smaller than the reference value, it is determined that the feature vector P and the feature vector N are related because the distance between the feature vector P and the feature vector N is short. Note that the reference value is a value used as a reference for determining whether or not the feature vectors are related in the association determination process. can be a value.

Then, when the feature vector P and the feature vector N are related, it is determined that the candidate customer is likely to purchase the investment trust, and at the same time, the distance between the feature vectors previously calculated is acquired as the degree of association. . In the present embodiment, the smaller (closer) the value of the distance between the feature vector P and the feature vector N, that is, the higher the degree of relevance between the feature vector P and the feature vector N, the higher the likelihood of purchasing the investment trust. means high.

FIG. 7 shows a diagram for explaining the relationship between pattern distributions of each transaction data. Even for the same customer (for example, Hanako Yamada), each transaction data changes day by day. Then, the pattern distribution (corresponding to the feature vector N) of the daily transaction data of a customer (for example, Hanako Yamada) classified into customer group A is the transaction data when the customer (for example, Hanako Yamada) purchased an investment trust in the past. If it is related to the data pattern distribution (corresponding to the feature vector P), then this is the timing when the customer (for example, Hanako Yamada) has a high possibility of purchasing an investment trust.

In the figure, for example, the pattern distribution of transaction data for customer Hanako Yamada on January 7, 2019 (as of two weeks ago) and January 14, 2019 (as of one week ago) are both It is not related to the pattern distribution of each transaction data at the time of trust purchase. On the other hand, as a result of each transaction data changing with time, on January 21, 2019 (at present), the pattern distribution of transaction data for customer Hanako Yamada and each transaction at the date and time of past investment trust purchases by customer Hanako Yamada It is related to the pattern distribution of data. In other words, as of January 21, 2019 (at the present time), the pattern distribution of transaction data at the present time is the same as when customer Hanako Yamada herself actually purchased an investment trust in the past. It means that it is the right time to sell investment trust products to customer Hanako Yamada at the present time when there is a high possibility of purchasing.

Here, since each transaction data changes from moment to moment, if the transaction data changes significantly after this, the pattern distribution of transaction data for customer Hanako Yamada and the date and time of past investment trust purchases for customer Hanako Yamada are no longer associated with the pattern distribution of each transaction data in . In such a case, it can be said that the customer Hanako Yamada is already in a situation where there is no high possibility of purchasing an investment trust, and it can be said that the appropriate timing to sell investment trust products to the customer Hanako Yamada has been missed.

In addition, when a plurality of investment trust purchase dates are specified and transaction data for a plurality of purchase dates are acquired, feature vectors P (P1, P2, P3 . . . ) and feature vectors N , and when the distance between any one feature vector P and feature vector N is smaller than a reference value, it can be determined that they are related. Furthermore, when it is determined to be associated with a plurality of feature vectors P, it can be said that the possibility of purchasing the investment trust again is higher. can be changed to a greater extent. Alternatively, the distance to be acquired as the degree of association may be the maximum value among the plurality of distances acquired when determining the association between the feature vector P (P1, P2, P3, . . . ) and the feature vector N, or It can also be the average value of the distances of

S8: If it is determined that the feature vector P and the feature vector N are related as a result of the association determination process, the process proceeds to S9. If not determined to be related, the process proceeds to S10.

S9: Extract the candidate customer as a prospective customer who is predicted to have a high possibility of purchasing an investment trust at the present time. Also, the distance between the feature vectors previously calculated is acquired as the degree of association.

S10: Determine whether or not there is an unprocessed candidate customer. If there is an unprocessed candidate customer, go to S1 again. When this process has been executed for all candidate customers, this process ends.

S21: On the other hand, if the candidate customer has no experience of purchasing an investment trust in the past in S2, the management server 30 selects the candidate customer and the customer information Determine customers (referred to as similar customers) having similar or related (customer attribute information). For example, customers with similar customer attributes such as age, gender, occupation, annual income, etc. are likely to purchase investment trusts at similar timings under similar transaction data patterns. It's for.

S22: The management server 30 acquires from the processing DB 40 the transaction data at the time when the similar customer determined in S21 purchased the investment trust in the past (or for a predetermined period before the purchase corresponding to immediately before the purchase). The transaction data to be acquired is not only one type of transaction data, but at least two or more types of transaction data as of a specific date.

If there are multiple similar customers, the multiple similar customers may be determined in S21, and all the transaction data at the time when the multiple similar customers have purchased investment trusts in the past may be obtained in S22.

S23: The management server 30 calculates a feature vector P' from the transaction data pattern (combination of transaction data (values)) acquired in S22. The calculated feature vector P' indicates the feature amount of the transaction data situation of the similar customer at the time when the similar customer purchased the past investment trust.

Further, when the transaction data at the time when the plurality of similar customers have purchased investment trusts in the past is obtained in S22, a plurality of feature vectors P' (P'1, P'2, P'3 . . . ) are calculated. You may

S24: The management server 30 acquires the current transaction data for the candidate customer classified into the customer group B from the processing DB 40 this time. The transaction data at the current point in time is the transaction data last updated on the processing DB 40 . Also, the transaction data to be acquired is the same type of transaction data as corresponding to the transaction data acquired in S22.

S25: The management server 30 calculates a feature vector N from the transaction data pattern (combination of transaction data (values)) acquired in S24. The calculated feature vector N indicates the feature amount of the candidate customer's transaction data situation at the current time of the candidate customer.

S26: The management server 30 executes a relationship determination process between the feature vector P' and the feature vector N. For customers classified into customer group B who have no experience of purchasing investment trusts in the past, the feature vector P' of the transaction data of the customer classified into customer group A at the time of past purchase and the current transaction of the customer themselves The distance between the data and the feature vector N is calculated, and if the calculated distance is smaller than the reference value, the distance between the feature vector P' and the feature vector N is close, so the feature vector P' and the feature vector N are considered to be related. judge.

FIG. 8 shows a diagram for explaining the relationship between pattern distributions of transaction data. Even for the same customer (Ichiro Suzuki, for example), each transaction data changes day by day and hour by hour. The pattern distribution (corresponding to feature vector N) of daily transaction data of a customer (eg, Ichiro Suzuki) classified into customer group B is similar to that of a customer (eg, Hanako Yamada) who belongs to customer group A and has similar or related customer attributes. ) is related to the pattern distribution of transaction data (corresponding to the feature vector P′) when the investment trust was purchased in the past, this is the time when the customer (Ichiro Suzuki, for example) can purchase the investment trust. It is a sensitive timing.

In the figure, for example, on January 7, 2019 (as of two weeks ago) and January 14, 2019 (as of one week ago), the transaction data pattern distribution for customer Ichiro Suzuki, who has never purchased an investment trust in the past, is None of them are related to the pattern distribution of each transaction data at the date and time of past investment trust purchases of customer Hanako Yamada, who has experience of purchasing investment trusts in the past. On the other hand, the pattern distribution of transaction data for customer Ichiro Suzuki on January 21, 2019 (at present) and the pattern distribution of each transaction data at the date and time of past investment trust purchases for customer Hanako Yamada, who has experience purchasing investment trusts in the past is related. In other words, on January 21, 2019 (at the present time), when customer Hanako Yamada, who has a customer attribute with a similar or related relationship to the current transaction data pattern distribution of customer Ichiro Suzuki, has actually purchased an investment trust in the past. This means that it is the right time to sell investment trust products to the customer, Ichiro Suzuki, at a time when the possibility of purchasing investment trusts is high.

As a result of the relationship determination process, if the feature vector P' and the feature vector N are related (S8: YES), the candidate customer is regarded as a prospective customer who is predicted to have a high possibility of purchasing an investment trust at the present time, The degree of association is extracted together with the previously calculated distance between the feature vectors (S9). Also, it is determined whether or not there is an unprocessed candidate customer (S10), and if there is an unprocessed candidate customer, the process proceeds to S1 again. When this process has been executed for all candidate customers, this process ends.

In the past, the relationship between target customers and needs was judged based on experience and knowledge, or based only on one or more data values (for example, the amount of data values, or match/disagreement with predetermined values, etc.). , in this embodiment, the determination is based on mutual patterns (reciprocal combinations) or relative patterns (relative combinations) of various transaction data values.

For example, among multiple transaction data, one transaction data value (time deposit account balance, etc.) and another transaction data value changed to a high value (ordinary deposit account balance, etc.) both changed in a low range. However, there are cases where the customer's willingness to purchase investment trusts increases when both transaction data values change to moderately high values, which cannot be said to be high. If we focus only on the amount of any one transaction data value, we will miss this increase in willingness to purchase investment trusts.

That is, according to the present embodiment, it is possible to extract target customers whose needs are expected to be high, although it was difficult to extract them by the conventional method. In addition, based on the customer's past and present transaction data, which changes daily, the timing of the ease of buying financial products for each individual customer is quantified and determined by calculation. Therefore, the sales staff can improve sales efficiency by proposing and selling financial products at an appropriate timing specific to individual customers.

(Supplement 1)
FIG. 9 shows a diagram for explaining the relation of index pattern distribution based on each transaction data. The transaction data A to E shown in FIGS. 7 and 8 do not necessarily have to correspond one-to-one with each transaction data. For example, let A to E be indices as follows. Each metric is metric data comprising one or more of transaction data, customer information, and/or financial policy information.
A: “Risk tolerance” . Index data based on the balance of ordinary deposits, etc. D: “Investment capacity”: Balance of ordinary deposits, balance of liquid deposits, balance of investment trusts, etc. Indicator data E: “Investment timing”: Customer information, deposits and withdrawals of ordinary deposits , bonus payment date, etc.)

In the customer, each transaction data changes with the use of financial services for each customer, and the index data also changes. Then, the pattern distribution of the customer's daily index data (corresponding to the feature vector N) is the pattern distribution of the index data (corresponding to the feature vector P and the feature vector P') when the customer purchased the investment trust in the past. If so, that is when the customer is most likely to purchase the mutual fund.

As a result, from the viewpoint of extracting customers who are more likely to purchase, based on current transaction data, customer information, and/or asset management policy information, more effective and realistic indicators are created, and the indicators Based on the mutual pattern distribution of , it is possible to determine whether the customer is likely to purchase an investment trust.

(Supplement 2)
In the case of predetermined transaction data, for example, in the case of a customer who has purchased an investment trust when the savings account balance was 3,000,000 yen in the past, if the current savings account balance is around 3,000,000 yen, then They are determined to be related because the past transaction data match.

On the other hand, if the current savings account balance is around 5,000,000 yen, it may be determined that the current and past transaction data are not related. However, a customer who has purchased an investment trust at 3 million yen in the past is likely to purchase an investment trust at 5 million yen. In such a case, rather than being irrelevant to a high bank account balance, a current bank balance that is higher than the bank balance at the time of the previous purchase may be considered relevant.

Specifically, if there is this type of predetermined transaction data, the transaction data at the time of the purchase of the investment trust in the past is acquired, and the transaction data at the current time is the transaction data at the time of the purchase of the investment trust in the past. If it is greater than , the current transaction data is corrected so as to match or approximate the value of the transaction data at the time the investment trust was purchased in the past. In addition, a feature vector can be calculated including this type of transaction data as one piece of transaction data.

It should be noted that the reverse is also true if this type of predetermined transaction data is of a less desirable type, such as risk tolerance. In other words, if the current transaction data is smaller than the transaction data at the time the investment trust was purchased in the past, the transaction data at the current time will match or approximate the value of the transaction data at the time the investment trust was purchased in the past. Correct to In addition, a feature vector can be calculated including this type of transaction data as one piece of transaction data.

(Sales destination priority list creation process)
When the management server 30 receives a sales destination priority list acquisition request or display request from the sales terminal 50 of the salesperson, the candidate customers extracted by the prospective customer extraction process (S9) are sorted in order of priority (acquired relevance Create a sales destination priority list arranged in descending order of distance/shortest acquired distance). Also, the management server responds with the created sales destination priority list based on the acquisition request from the sales terminal 50 .

FIG. 10 shows an example of a sales destination priority list according to this embodiment. The sales person acquires the sales destination priority list screen from the management server 10 on the sales terminal 50 and displays it. The sales destination priority list 51 has, for example, a sales branch selection field 52, a sales representative selection field 53, a financial product selection field 54, a customer number designation field 55, and a list 56. FIG.

The business branch selection column 52 is a column for selecting a business branch. Customers who have an account at the selected business branch are target candidate customers of the business destination priority list 51 .

The salesperson selection column 53 is a column for selecting a salesperson. The customer in charge of the selected salesperson becomes the target candidate customer of the sales destination priority list 51 .

The financial product selection column 54 is a column for selecting the type of financial product that is the key for list search. Customers who are likely to purchase the selected financial product become target candidate customers in the sales destination priority list 51 .

The number-of-customers specification column 55 is a column for specifying and selecting the number of customers (number of cases) to be displayed in the list 56 . A list 56 displays a specified number of customers from the customers having the highest priority and highest score. A salesperson specifies, for example, the number of customers that can be approached on a given day.

A list 56 is a sales destination list in which the customers extracted by prospective customer extraction processing for the selected financial product among the customers who have an account in the selected sales branch and are in charge of the selected sales representative are arranged in order of priority. is. The list 56 also has items such as priority 56a, score 56b, customer group 56c, customer information 56d, and so on.

The priority 56a indicates the order of priority to open. The higher the degree of association acquired in S9 (the shorter the distance acquired), the higher the likelihood of purchasing the investment trust. Therefore, the priority 56a corresponds to the degree of association (distance) acquired. In other words, on the list 56, the customers are arranged in descending order of degree of association (in descending order of distance) acquired together with the customers extracted by the prospective customer extracting process. The higher the priority 56a, the higher the likelihood of purchase of the selected financial product. Therefore, the salesperson can conduct efficient sales by approaching customers in order from the highest priority 56a.

The score 56b is the value of the degree of association (distance) itself or its correction value. A salesperson can grasp the degree of purchase prospect for each customer by a specific numerical value.

The customer group 56c indicates whether the customer has purchased the financial product 54 or not. For example, in line with the above, customers who have experience purchasing investment trusts in the past and actually still hold investment trusts (targets for additional purchasers of investment trusts) are A1, and customers who have experience purchasing investment trusts in the past Customers who do not currently hold investment trusts (target repurchasers of investment trusts) are A2, customers who have never purchased investment trusts in the past and do not currently hold investment trusts (target new purchasers of investment trusts) is B. It is reference information for the sales staff when proposing financial products and conducting business.

The customer information 56d is customer information including the customer's customer number, name, age, and so on. The salesperson approaches the customer while referring to the customer information 56d on the list 56. FIG.

It should be noted that at the time of creating the sales destination priority list, based on the past negotiation history of the sales promotion support system 20, customers who are already in business or have already been in business can be excluded from the business destination priority list 51 (list 56). is also possible. This is to avoid duplicate sales.

In addition, in the list 56, if the difference between the score 56b of the customer and the score 56b of the next priority customer is large (for example, the score is 0.1 or more), the customer and the next customer are separated. The display 56e is indicated by arrows, lines and colors, for example. For example, in the case of the display 56e in FIG. 10, since the score difference between the priority 6 and the priority 7 is large, the salesperson should follow the display 56e to priority 1 to 6, especially when business hours are limited. By approaching only the customers with priority 1 to 7, it is possible to optimize the time-effectiveness compared with the case of approaching the customers with priority 1 to 7, for example. In this case, the customers with priority levels 1 to 10 in the list 56 are further divided into priority groups such as first priority group 1 to 6 and second priority group 7 to 10 according to display 56e. It has a meaning.

As described above, according to the sales destination priority list 51, it is possible to list customers who are appropriate to be approached at the time when the sales destination priority list 51 is created. A salesperson can improve sales efficiency by proposing and selling financial products based on the sales destination priority list 51 .

<Modification>
Next, the sales product priority list will be explained. The sales destination priority list in FIG. 10 is a list of customers who are highly likely to purchase the financial product (for example, investment trust) as a key, with the priority assigned thereto. The business product priority list according to this modified example uses a customer (for example, Hanako Yamada) as a key, and gives priority to financial products (types of financial products) that are highly likely to be purchased by the customer among a plurality of types of financial products. It is a list with degrees.

FIG. 11 shows an example of a business product priority list (modification) according to this embodiment. The sales product priority list 61 has, for example, a customer number input field 62, a search button 63, customer information 64, and a list 65. FIG.

For example, assume that a customer (for example, Hanako Yamada) visits a customer service counter and proposes a recommended financial product to the customer. The salesperson inputs the customer number of the customer in the input field 62 on the sales terminal 50 and presses the search button 63 to display the customer information 64 and the list 65 of the customer.

A list 65 is a business product priority list in which each financial product that is highly likely to be purchased by the selected customer is arranged in order of priority.

The priority 65a indicates the order of priority to open. According to the priority 65a, customers are arranged in descending order of the degree of relevance acquired with each financial product (in ascending order of distance). The higher the priority 65a, the higher the likelihood of purchase of the selected financial product. Therefore, the salesperson can efficiently propose products by approaching the customer in order from the highest priority 65a.

The score 65b is the value of the degree of association (distance) itself or its correction value. A salesperson can grasp the degree of purchase prospect for each financial product by using a specific numerical value.

The financial product name 65c indicates the type and name of a specific financial product to be proposed (recommended) to the customer. In addition, it is possible to display related information corresponding to specific financial products such as "upper limit" and "latest purchase date". The salesperson makes a product proposal to the customer while referring to the financial product name 65c on the list 65. FIG.

FIG. 12 shows a diagram for explaining the relationship between pattern distributions of transaction data. As described above, each transaction data changes day by day even for the same customer. Then, the pattern distribution of daily transaction data of a customer (for example, Hanako Yamada) is compared with the pattern distribution of transaction data when the customer has purchased various types of financial products (for example, investment trusts and car loans) in the past. If so, then that is when the customer (eg, Hanako Yamada) is most likely to purchase that type of financial product.

In addition, if the customer (for example, Hanako Yamada) has never purchased a type of financial product (such as a free loan, card loan, or educational loan), the customer has purchased the financial product in the past, and the Determine similar customers with customer attributes that are similar or related to the customer (e.g. Hanako Yamada), and the similar customers have used various types of financial products (e.g. free loans, card loans, educational loans) in the past Determine the relationship with the pattern distribution of transaction data at the time of purchase.

Specifically, regarding investment trusts, on January 21, 2019 (at the present time) when a customer (for example, Hanako Yamada) visited the customer service counter, the pattern distribution of transaction data of customer Hanako Yamada and the past investment of customer Hanako Yamada It is not related to the pattern distribution of each transaction data at the time of trust purchase.

Next, regarding personal car loans, on January 21, 2019 (at the present time), the pattern distribution of transaction data for customer Hanako Yamada and the pattern distribution of each transaction data at the date and time when customer Hanako Yamada purchased a personal car loan in the past are related. .

Next, regarding the free loan, since the customer (for example, Hanako Yamada) has never purchased a free loan in the past, there is no similarity or relationship with the customer (for example, Hanako Yamada) who has purchased a free loan in the past. A similar customer (for example, Taro Tanaka) who has the customer attribute is determined. On January 21, 2019 (current time), the pattern distribution of transaction data for customer Hanako Yamada and the pattern distribution of each transaction data for customer Taro Tanaka at the date and time of past free loan purchases are related.

Next, with regard to card loans, since the customer (for example, Hanako Yamada) has never purchased a card loan in the past, there is no similarity or relationship with the customer (for example, Hanako Yamada) who has purchased a card loan in the past. A similar customer (for example, Jiro Suzuki) who has customer attributes is determined. On January 21, 2019 (current time), the pattern distribution of transaction data for customer Hanako Yamada and the pattern distribution of each transaction data for customer Jiro Suzuki at the date and time of past card loan purchases are related.

Next, regarding the education loan, since the customer (for example, Hanako Yamada) has never purchased an education loan in the past, there is no similarity or relationship with the customer (for example, Hanako Yamada) who has purchased an education loan in the past. A similar customer (for example, Kazuko Sato) who has the customer attribute is determined. As of January 21, 2019 (at the present time), the pattern distribution of transaction data for customer Hanako Yamada is not related to the pattern distribution of each transaction data at the date and time of past education loan purchases for customer Kazuko Sato.

As described above, the relationship determination unit 303 of the management server 30 according to the present modification determines the pattern distribution of transaction data for customers and each transaction at the date and time of purchase of the financial product in the past for each type of financial product. Determine association with pattern distribution of data.

Next, the extracting unit 304 extracts the type of financial product to which the pattern distribution of the customer's transaction data is related by the relation determination unit 303 as a financial product to be sold, together with the degree of relevance indicating the priority. Specifically, car loans, free loans, and card loans among the financial products are extracted as financial products to be sold along with the degree of association, such as the distance between the feature vectors described above, indicating the degree of association. Then, the sales destination list creation unit 305 creates sales product list information in which each type of financial product extracted by the extraction unit 304 is arranged in order of priority (corresponding to the degree of relevance) (FIG. 11).

It should be noted that whether or not the user has purchased an investment trust in the past can refer to an example of the investment trust information in FIG. 4D, for example. Similarly, by referring to the unillustrated financial institution system 10 (sales management system for managing sales performance of various financial products), it is possible to determine whether or not investment trusts have been purchased in the past. be.

In addition, with investment trusts as the key, a list (investment It is also possible to use a trust product priority list). In this case, for each investment trust product, it is possible to determine the relationship between the pattern distribution of transaction data in the customer and the pattern distribution of each transaction data at the date and time when the investment trust product was purchased in the past.

<Summary>
As described above, according to the sales support system 100 according to the present embodiment, it is possible to accurately extract customers who are expected to have needs for predetermined financial products, and to support efficient sales activities in financial institutions.

It should be noted that, although the preferred embodiment of the invention has been described with reference to specific examples, these specific examples should not depart from the broader spirit and scope of the invention as defined in the appended claims. Obviously, various modifications and changes can be made to the examples. Thus, the details of the specific examples and accompanying drawings should not be construed as limiting the present invention.

The management server 30 can be called a sales support device, a prospective customer extraction device, a business destination list creation device, or the like by focusing on the function of the server.

<Invention group extracted from this embodiment>
The features of the group of inventions extracted from the above-described embodiments will be described below.

(Appendix A1)
A sales support device in a financial institution,
acquisition means for acquiring customer transaction data at a financial institution;
a relationship determining means for determining the relationship between the customer's first transaction data at the time of purchase of a financial product in the past and the customer's second transaction data at the present time;
extraction means for extracting a customer for whom the relationship determination means determines that the first transaction data and the second transaction data are related;
an output means for outputting the customers extracted by the extraction means;
A sales support device characterized by having:

(Appendix A2)
A sales support device in a financial institution,
Acquisition means for acquiring at least two or more different types of transaction data of customers in a financial institution;
a relationship determining means for determining a relationship between a pattern of the customer's first transaction data at the time of purchase of a financial product in the past and a pattern of the customer's second transaction data at the present time;
extracting means for extracting the customer determined by the relationship determining means that the pattern of the first transaction data and the pattern of the second transaction data are related;
an output means for outputting the customers extracted by the extraction means;
A sales support device characterized by having:

(Appendix A3)
The output means, when a plurality of customers are extracted by the extraction means, outputs the customers in descending order of the degree of relevance determined by the relevance determination means;
The sales support device according to Supplementary Note A1 or Supplementary Note A2, characterized by:

(Appendix A4)
When a plurality of customers are extracted by the extraction means, the output means outputs to a terminal a list arranged in order of the degree of relevance determined by the relevance determination means to the terminal.
The sales support device according to Supplementary Note A1 or Supplementary Note A2, characterized by:

(Appendix A5)
The output means, when outputting the customers in descending order of the degree of relevance, determines the degree of relevance between the first customer and the second customer with the next highest degree of relevance after the first customer. indicating a division between the first customer and the second customer when the difference is greater than a predetermined value;
The sales support device according to appendix A3 or appendix A4, characterized by:

(Appendix A6)
For predetermined transaction data among the transaction data of the customer,
the association determining means, when the second transaction data is larger than the first transaction data, matching or approximating the second transaction data to the first transaction data;
The sales support device according to Supplementary Note A1 or Supplementary Note A2, characterized by:

(Appendix A7)
For predetermined transaction data among the transaction data of the customer,
the relevance determining means, when the second transaction data is smaller than the first transaction data, matching or approximating the second transaction data to the first transaction data;
The sales support device according to Supplementary Note A1 or Supplementary Note A2, characterized by:

(Appendix A8)
If there are multiple times when the financial product was purchased in the past,
The relationship determining means determines a relationship between each of the first transaction data at the plurality of past points in time and the second transaction data;
the extracting means extracting customers for whom the relationship determining means determines that the first transaction data and the second transaction data at least one or more of the past points in time are related;
The sales support device according to appendix A1, characterized by:

(Appendix A9)
If there are multiple times when the financial product was purchased in the past,
The relationship determination means determines a relationship between each of the patterns of the first transaction data at the plurality of past points in time and the pattern of the second transaction data;
The extracting means extracts customers for whom the relationship determining means determines that at least one pattern of the first transaction data at the past point in time is related to the second transaction data;
The sales support device according to appendix A2, characterized by:

(Appendix A10)
the financial product is an investment trust product;
The sales support device according to any one of Appendices A1 to 9, characterized by:

(Appendix B1)
A sales support device in a financial institution,
acquisition means for acquiring customer transaction data at a financial institution;
a relationship determining means for determining a relationship between first transaction data of a first customer at the time of purchasing a financial product in the past and second transaction data of a second customer who has not purchased the financial product at the current time;
extraction means for extracting the second customer determined by the relationship determination means that the first transaction data and the second transaction data are related;
output means for outputting the second customer extracted by the extraction means;
A sales support device characterized by having:

(Appendix B2)
A sales support device in a financial institution,
Acquisition means for acquiring at least two or more different types of transaction data of customers in a financial institution;
A relationship for determining a relationship between a first transaction data pattern of a first customer at the time of purchasing a financial product in the past and a second transaction data pattern of a second customer who has not purchased the financial product at the current time determination means;
extraction means for extracting the second customer determined by the relationship determination means that the pattern of the first transaction data and the pattern of the second transaction data are related;
output means for outputting the second customer extracted by the extraction means;
A sales support device characterized by having:

(Appendix B3)
the first customer is a customer whose customer information is related to the customer information of the second customer;
The sales support device according to Supplementary Note B1 or Supplementary Note B2, characterized by:

(Appendix B4)
the financial product is an investment trust product;
The sales support device according to any one of appendices B1 to B3, characterized by:

(Appendix C1)
A sales support device in a financial institution,
an acquisition means for acquiring transaction data of a customer at a financial institution;
a relationship determination means for determining, for each type of financial product, the relationship between the first transaction data of the customer at the time of purchase of the financial product in the past and the second transaction data of the customer at the present time;
extracting means for extracting a type of financial product determined by the relationship determination means to be related to the first transaction data and the second transaction data;
an output means for outputting the type of financial product extracted by the extraction means;
A sales support device characterized by having:

(Appendix C2)
A sales support device in a financial institution,
Acquisition means for acquiring at least two or more different types of transaction data of one customer in a financial institution;
a relation determining means for determining, for each type of financial product, a relation between a pattern of the customer's first transaction data at the time of purchase of the financial product in the past and a pattern of the customer's second transaction data at the present time;
extracting means for extracting a type of financial product for which the relationship determining means determines that the pattern of the first transaction data and the pattern of the second transaction data are related;
an output means for outputting the type of financial product extracted by the extraction means;
A sales support device characterized by having:

(Appendix D1)
A sales support device in a financial institution,
an acquisition means for acquiring transaction data of a second customer in a financial institution;
For each type of financial product, the first transaction data of the first customer at the time of purchasing the financial product in the past and the second transaction data of the first second customer who has not purchased the financial product at the present time in the past a relevance determination means for determining the relevance of
extracting means for extracting a type of financial product determined by the relationship determination means to be related to the first transaction data and the second transaction data;
an output means for outputting the type of financial product extracted by the extraction means;
A sales support device characterized by having:

(Appendix D2)
A sales support device in a financial institution,
Acquisition means for acquiring at least two or more different types of transaction data of a second customer in a financial institution;
For each type of financial product, the pattern of the first transaction data of the first customer at the time of purchasing the financial product in the past, and the second transaction data of the first second customer who has not purchased the financial product at the present time. relevance determination means for determining relevance to data patterns;
extracting means for extracting a type of financial product for which the relationship determining means determines that the pattern of the first transaction data and the pattern of the second transaction data are related;
an output means for outputting the type of financial product extracted by the extraction means;
A sales support device characterized by having:

(Appendix E1)
A business contact list creation device in a financial institution,
Acquisition means for acquiring customer information of a customer in a financial institution;
Extraction means for extracting a plurality of customers who are business destinations among the customers together with information indicating priority;
creation means for creating business contact list information in which the plurality of customers are arranged in order of priority;
output means for outputting the sales destination list information to a sales terminal;
A business destination list creation device characterized by having:

(Appendix E2)
The plurality of customers are customers whose transaction data at the past point in time when they purchased financial products in the past and their current transaction data are related;
The business destination list creation device according to appendix E1, characterized by:

(Appendix E3)
The plurality of customers are customers whose transaction data pattern at a past point in time when they purchased financial products in the past and their current transaction data pattern are related;
The business destination list creation device according to appendix E1, characterized by:

(Appendix E4)
the priority is the degree of relevance;
The business destination list creation device according to appendix E2 or 3, characterized by:

(Appendix F1)
A sales terminal in a financial institution,
a sending means for sending a request to obtain business contact list information to the server device;
Receiving means for receiving the business destination list information in which a plurality of customers serving as business destinations are arranged in descending order of priority;
A sales terminal characterized by having

(Appendix F2)
The plurality of customers are customers whose transaction data at the past point in time when they purchased financial products in the past and their current transaction data are related;
A sales terminal according to Appendix F1, characterized by:

(Appendix F3)
The plurality of customers are customers whose transaction data pattern at a past point in time when they purchased financial products in the past and their current transaction data pattern are related;
A sales terminal according to Appendix F1, characterized by:

(Appendix F4)
the priority is the degree of relevance;
A sales terminal according to appendix F2 or 3, characterized by:

(Appendix G1)
to the computer,
a sending means for sending a request to obtain business contact list information to the server device;
Receiving means for receiving the business destination list information in which a plurality of customers serving as business destinations are arranged in descending order of priority;
display means for displaying the business contact list information;
display program to function as

(Appendix G2)
The plurality of customers are customers whose transaction data at the past point in time when they purchased financial products in the past and their current transaction data are related;
The display program according to appendix G1, characterized by:

(Appendix G3)
The plurality of customers are customers whose transaction data pattern at a past point in time when they purchased financial products in the past and their current transaction data pattern are related;
The display program according to appendix G1, characterized by:

(Appendix G4)
the priority is the degree of relevance;
The display program according to appendix G2 or 3, characterized by:

(Appendix H1)
A server device of a financial institution,
Acquire customer transaction data in financial institutions,
extracting the customer if the obtained transaction data of the customer is similar to the transaction data of the customer at the time of purchase of financial products in the past;
A server device characterized by:

(Appendix H2)
A server device of a financial institution,
Acquire multiple types of customer transaction data at financial institutions,
If the status of the acquired transaction data of multiple types of customers is similar to the status of the customer's transaction data at the time of purchase of financial products in the past, extracting the customer in the sales destination list;
A server device characterized by:

(Appendix H3)
extracting the plurality of customers in descending order of similarity when a plurality of the customers are extracted from the business destination list;
The server device according to appendix H1 or 2, characterized by:

10 financial institution system 20 sales promotion support system 30 management server 40 processing DB
50 sales terminal 70 network 100 sales support system 301 data acquisition unit 302 feature amount calculation unit 303 relation determination unit 304 extraction unit 305 business destination list creation unit 306 output unit

Claims (15)

Classification means for classifying a plurality of target customers into groups according to whether or not they have purchased financial products based on customer transaction data;
Among the customer transaction data classified by the classification means, the candidate customer's transaction data feature quantity and the transaction data feature quantity of the candidate customer who have at least purchased financial products in the past are used to identify the candidate customer. a degree-of-relevance obtaining means for obtaining a degree of relevance, which is the degree of likelihood of purchasing a financial product;
Sales destination priority list creation means for listing the candidate customers whose relevance is acquired by the relevance acquisition means in order of priority based on the relevance;
A sales support device having With respect to said candidate customer, with respect to a plurality of types of financial instruments , said degree-of-relevance acquisition means acquires the degree of relevance of each financial instrument, and based on the degree of relevance of each of said financial instruments, selects financial instruments that are highly likely to be purchased by said customer. sales product priority list creation means for listing in order of priority;
The sales support device according to claim 1, further comprising: customer exclusion means for excluding customers who are in business or who have already been in business from the candidate customers listed in order of priority based on past negotiation history;
The sales support device according to claim 1 or 2, further comprising: The degree-of-relevance obtaining means acquires customer attribute information of the customer and the candidate customer in addition to the feature amount of the transaction data of the customer who has purchased financial products in the past and the feature amount of the transaction data of the candidate customer. use further,
The sales support device according to any one of claims 1 to 3. The degree-of-relevance obtaining means uses the feature amount of the transaction data of the customer who has purchased financial products in the past when obtaining the degree of relevance for a candidate customer who has not purchased financial products in the past,
The sales support device according to any one of claims 1 to 4. The sales support device
A classification procedure for classifying a plurality of target customers into groups according to whether or not they have purchased financial products based on customer transaction data;
Of the transaction data of customers classified by the classification procedure, using the feature amount of transaction data of customers who have at least purchased financial products in the past and the feature amount of transaction data of candidate customers, a relevance obtaining procedure for obtaining a relevance that is a degree of likelihood of purchasing a financial product;
a sales destination priority list creation procedure for listing the candidate customers whose relevance is acquired by the relevance acquisition procedure in order of priority based on the relevance;
Sales support method to carry out. With respect to said candidate customer, for multiple types of financial instruments, the degree of relevance of each financial instrument is acquired by said degree of relevance acquisition procedure, and based on the degree of relevance of each of said financial instruments, financial instruments that are highly likely to be purchased by said customer are selected. A procedure for creating a priority list of sales products listed in order of priority;
7. The sales support method according to claim 6, further comprising: a customer exclusion procedure for excluding customers who are in business or who have already been in business from the candidate customers listed in order of priority based on past negotiation history;
8. The sales support method according to claim 6 or 7, further comprising: The degree-of-association acquisition step obtains customer attribute information of the customer and the candidate customer in addition to the feature amount of the transaction data of the customer who has purchased financial products in the past and the feature amount of the transaction data of the candidate customer. use further,
The sales support method according to any one of claims 6 to 8. The degree-of-relevance obtaining procedure uses a feature amount of transaction data of a customer who has purchased financial products in the past when obtaining the degree of relevance for a candidate customer who has not purchased financial products in the past,
The sales support method according to any one of claims 6 to 9. the computer ,
Classification means for classifying a plurality of target customers into groups according to whether or not they have purchased financial products based on customer transaction data;
Among the customer transaction data classified by the classification means, the candidate customer's transaction data feature quantity and the transaction data feature quantity of the candidate customer who have at least purchased financial products in the past are used to identify the candidate customer. a degree-of-relevance obtaining means for obtaining a degree of relevance, which is the degree of likelihood of purchasing a financial product;
Sales destination priority list creation means for listing the candidate customers whose relevance is acquired by the relevance acquisition means in order of priority based on the relevance;
program to function as With respect to said candidate customer, with respect to a plurality of types of financial instruments, said degree-of-relevance acquisition means acquires the degree of relevance of each financial instrument, and based on the degree of relevance of each of said financial instruments, selects financial instruments that are highly likely to be purchased by said customer. sales product priority list creation means for listing in order of priority;
12. The program of claim 11 for further functioning as a customer exclusion means for excluding customers who are in business or who have already been in business from the candidate customers listed in order of priority based on past negotiation history;
13. The program according to claim 11 or 12 for further functioning as a The degree-of-relevance obtaining means acquires customer attribute information of the customer and the candidate customer in addition to the feature amount of the transaction data of the customer who has purchased financial products in the past and the feature amount of the transaction data of the candidate customer. use further,
14. A program according to any one of claims 11-13. The degree-of-relevance obtaining means uses the feature amount of the transaction data of the customer who has purchased financial products in the past when obtaining the degree of relevance for a candidate customer who has not purchased financial products in the past,
15. A program according to any one of claims 11-14.

Images