JP5444096B2 - Information analyzer - Google Patents

Description

  The present invention relates to a data processing technique, and more particularly to a technique for analyzing customer information.

  In recent years, attempts have been made to obtain useful information in business by causing a computer to analyze various information. In the following Patent Document 1, the present applicant proposes a technique for analyzing product sales information and creating information for supporting user sales activities. Specifically, with regard to the area where the purchaser of the product resides (hereinafter also referred to as “area”), the purchaser pays attention to a group of areas (hereinafter also referred to as “area cluster”) with similar attributes of residents. Proposes a technique for creating useful information for merchandise sellers by analyzing sales information based on the area cluster in which they live.

JP 2009-169698 A

  As competition between companies intensifies, companies will promote sales to promising customers who are expected to generate more revenue in the future than current revenues in order to efficiently increase revenues per customer. It is required to carry out activities. However, it has not been easy to identify promising customers among many customers.

  The present invention has been made in view of these problems, and its main purpose is to provide a technique for creating information useful for merchandise sellers by analyzing customer information based on area clusters. is there.

  In order to solve the above problems, an information analysis apparatus according to an aspect of the present invention provides a correspondence relationship between each of a plurality of geographically partitioned areas and an area cluster obtained by grouping areas having similar attributes regarding residents. Area cluster information holding unit to be held, customer information holding unit to hold information on revenue obtained from each of a plurality of customers, and revenue obtained from customers residing in each area cluster for each of the plurality of area clusters The area cluster identification unit that identifies area clusters with relatively large revenues obtained from customers and customers who reside in area clusters with relatively large revenues have relatively small revenues. A customer extraction unit that extracts a customer as a customer who is likely to generate a larger revenue than the currently obtained revenue in the future.

  It should be noted that any combination of the above-described constituent elements and a representation of the present invention converted between an apparatus, a method, a system, a program, a recording medium storing the program, and the like are also effective as an aspect of the present invention.

  According to the present invention, sales promotion activities of merchandise sellers can be effectively supported.

It is a figure which shows the structure of the analysis system of embodiment. It is a figure which shows the structure of customer information. It is a block diagram which shows the function structure of the information analyzer of FIG. It is a figure which shows the structure of area cluster information. It is a figure which shows an example of the average profit per customer for every area cluster. It is a figure which shows the selection image of a prospective customer.

Before describing the embodiment of the present invention, an outline will be described first.
As competition between companies intensifies, companies have become a proposition to earn more from existing customers. However, focusing on promotional activities for all customers is not practical from a cost perspective and is not desirable from a cost-effective perspective. For this reason, we will identify customers who are likely to generate more revenue than the current revenue for the company in the future (hereinafter also referred to as “promising customers”), and carry out sales promotion activities on those prospective customers. It is desirable.

  Therefore, in this embodiment, an analysis system is proposed that applies the concept of area clusters in the analysis of corporate customer information. This analysis system selects and presents promising customers based on the idea that customers with similar attributes such as family structure and annual income, that is, customers who live in the same area cluster are likely to obtain similar revenue. To do. This effectively supports the company's sales promotion activities, for example, improving its cost effectiveness.

  FIG. 1 shows a configuration of an analysis system according to an embodiment. In the analysis system 100, the customer information DB 10, the information analysis device 12, and the information presentation device 14 are connected via known communication means such as LAN, WAN, and the Internet.

  The customer information DB 10 is a database server that holds company customer information. FIG. 2 shows a configuration of customer information held in the customer information DB 10. The customer information includes a customer ID for each of a plurality of customers, a customer name, an address that can identify at least a street, and a revenue obtained from the customer (provided by the customer). This revenue may be a value that allows each customer to compare the amount of revenue that the customer brings to the company, may be an absolute value that has meaning in the value itself, or a relative value that has meaning only in comparison with other customers. There may be. For example, it may be a sales amount to a customer, a transaction amount, or an amount of profit generated by a transaction with the customer. Further, instead of the revenue amount itself, an index value indicating the amount of revenue calculated from the revenue amount by a statistical method may be used. The customer information may further include various attribute information (profession, transaction record, etc.) regarding the customer.

  Returning to FIG. 1, the information analysis device 12 is an information processing device that analyzes customer information held in the customer information DB 10 and generates information on promising customers. The detailed configuration of the information analyzer 12 will be described later. The information presentation device 14 is a device that presents information about a promising customer, which is an analysis result of the information analysis device 12, to a user (such as a sales representative of a company), and may be a display or a printer, for example. Moreover, the information processing apparatus which hold | maintains the information of a prospective customer, processes suitably, and shows to a user may be sufficient.

  FIG. 3 is a block diagram showing a functional configuration of the information analysis apparatus 12 of FIG. Each block shown in the block diagram of the present specification can be realized in terms of hardware by an element such as a CPU of a computer or a mechanical device, and in terms of software, it can be realized by a computer program or the like. The functional block realized by those cooperation is drawn. Therefore, those skilled in the art will understand that these functional blocks can be realized in various forms by a combination of hardware and software. For example, each functional block in FIG. 3 may be stored in a recording medium as software, installed in the hard disk of the information analysis apparatus 12, and appropriately read into the main memory of the information analysis apparatus 12 and executed by the processor.

  The information analysis apparatus 12 includes an area cluster information holding unit 20 that is a data storage area, and a data processing unit 30 that executes various data processing. The area cluster information holding unit 20 holds area cluster information in which each of a plurality of area clusters, an area belonging to each area cluster, and a resident attribute of each area cluster are associated with each other.

  FIG. 4 shows a configuration of area cluster information held in the area cluster information holding unit 20. In the “area cluster” column of the same figure, area cluster identification information is set. In the “area” column, one or more areas belonging to the area cluster are set. For example, each of approximately 180,000 town-chomes throughout Japan may be set as an area and classified into any of about 50 area clusters. In the “population” column, the population of the area is set.

  In the “resident attribute” column, the resident attribute of the area cluster is set, and the resident attribute that is commonly applied to the areas belonging to the same area cluster is set. This inhabitant attribute includes a demographic attribute indicating demographic attribute data for each area cluster, and a psychographic attribute indicating attribute data relating to human psychology such as values and lifestyle of residents of each area cluster. included.

  Examples of demographic attributes include “nuclear family with relatively small children in their 30s and 40s”, “income is slightly higher than average, and many are university graduates”, “two children”, etc. . On the other hand, as an example of psychographic attributes, “For women in their 20s, brand, safety and economy are very important, but there is little environmental orientation”, “For women in their 30s, the brand is slightly emphasized, “Environmentally oriented” and “Risk tolerance is relatively high”. That is, the resident attribute of the area cluster is information indicating a consumer image living in the area cluster, and includes the age, income level, occupation, educational background, family structure, living environment, preferences, way of thinking, etc. of the consumer.

  In the “resident index value” field, a resident index value obtained by indexing the resident attributes of the area cluster is set. The resident index value is a plurality of types of index values obtained by indexing the degree of matching of the resident attributes of the area cluster with each of a plurality of types of evaluation criteria using a predetermined evaluation function. Specific examples of the inhabitant index values include average annual income, average number of households, average number of children per household, 30s ratio, 40s ratio, and the like. In other words, it can be said that the resident index value is obtained by converting the resident attribute into a plurality of types of numerical values for calculation processing by a computer.

  An example of a method for creating area cluster information will be described. The area cluster information is created using attribute information about each area, and various public statistical information, original estimation information, and questionnaire result information. The statistical information includes age ratio, gender ratio, occupation ratio, educational ratio, and the like. The estimation information includes average income, average asset, average land price, and the like. The questionnaire result information includes answer results such as lifestyle, values, and consumption preferences. The qualitative information is indexed by a predetermined evaluation function. An area cluster information creating unit (not shown) groups each area by cluster analysis using various attribute information converted into index values for each area as variables. Various index values used for the cluster analysis may be set as values in the resident index value column, and data to be set in the resident attribute column may be set based on human judgment based on the values in the resident index value column. Further, the sales results of various products in each area may be a variable of cluster analysis.

  Returning to FIG. 3, the data processing unit 30 includes a customer information acquisition unit 32, an area cluster identification unit 34, a customer extraction unit 36, and an analysis result output unit 38. The customer information acquisition unit 32 issues a predetermined query to the customer information DB 10 and acquires the customer information held in the customer information DB 10. The acquired customer information includes at least a customer ID related to each customer, information on a customer address that can identify the town level, and a revenue value. The analysis result output unit 38 transmits the information of the promising customer created by the customer extraction unit 36 to the information presentation device 14.

  The area cluster specifying unit 34 refers to the customer information acquired by the customer information acquiring unit 32 and totals the profits obtained by the companies from the customers residing in the town chome (area) belonging to each area cluster. Enables revenue comparison at. In the present embodiment, average profit per customer (hereinafter also referred to as “average profit per customer”) is calculated for each area cluster.

  In calculating the average revenue per customer, the area cluster specifying unit 34 may exclude customers with higher revenues in order to eliminate the influence of customers whose revenue is significantly higher than other customers. For example, customers arranged in a descending order of revenue may be excluded from the average revenue calculation process if the customer has a predetermined rank or higher or a customer whose profit is a predetermined value or higher. Conversely, in order to eliminate the influence of customers whose profits are significantly smaller than those of other customers, it is possible to exclude customers with lower profits. For example, customers that are less than a predetermined rank when arranged in descending order of revenue, or customers whose revenue is less than a predetermined value may be excluded from the average revenue calculation process. Furthermore, it is possible to exclude both higher-ranking customers and lower-ranking customers. Note that these threshold values may be set in advance as appropriate values that are assumed to be appropriate based on company knowledge and experience, and experiments using the analysis system 100, and may be appropriately adjusted.

  FIG. 5 shows an example of average revenue per customer for each area cluster. The horizontal axis of the figure shows 10 area clusters A to J, and the vertical axis shows the average profit per customer (unit: 100 yen / person). As described above with respect to revenue, the average revenue may also be a value that allows comparison of the average revenue per customer between area clusters.

  The area cluster specifying unit 34 compares the average profit per customer of each area cluster, and specifies an area cluster having a relatively large profit obtained from the customer as a “high profit area cluster” among the plurality of area clusters. For example, in FIG. 5, the area cluster G having the maximum average profit per customer may be a high profit area cluster. In addition, the area clusters C, F, G, and I having an average profit per customer that is higher than a predetermined rank (here, fourth or higher) may be used as a high profit area cluster. In addition, the area clusters C, F, and G having an average profit per customer of a predetermined value or more (here, 3 or more) may be set as a high profit area cluster.

  Returning to FIG. 3, the customer extraction unit 36 compares the profits obtained from each of the customers residing in the town (area) belonging to the high profit area cluster. Then, a customer whose profit is relatively low is extracted as a promising customer. For example, customers arranged in descending order of revenue may be selected as promising customers if the customer is less than a predetermined rank, or if the revenue is less than a predetermined value. FIG. 6 shows a selection image of promising customers. In the figure, the customers living in the high profit area cluster are arranged in descending order of the profits obtained from the customers. The customer extraction unit 36 selects the customer IDs “2567” to “1008”, which are the customers with lower ranks in FIG.

The operation of the analysis system 100 configured as above will be described.
The information analysis apparatus 12 receives a customer information analysis request (specifically, a promising customer extraction request) from the user, and starts a promising customer determination process. The customer information acquisition unit 32 of the information analysis device 12 acquires customer information from the customer information DB 10. The area cluster specifying unit 34 specifies a high profit area cluster having a relatively large profit obtained from the customer among the plurality of area clusters. The customer extraction unit 36 determines, as promising customers, among the plurality of customers who reside in the high-profit area cluster, those with relatively small profits brought to the company. The analysis result output unit 38 appropriately acquires attribute information about the promising customer from the customer information DB 10 and transmits information about the promising customer to the information presentation device 14. The information presentation device 14 provides the user with information on the prospective customer, and displays the information on, for example, a display.

  According to the analysis system 100 of the present embodiment, a customer who lives in an area belonging to a high-profit area cluster but currently brings low profits to the company can be presented as a promising customer to a sales person in the company. . Promising customers are likely to have similar attributes to customers that are currently generating significant revenue for the company, so depending on the business, they are likely to become large revenue-generating customers. A sales person in a company can improve profits efficiently by conducting sales promotion activities on promising customers more than other customers. For example, in the case of an insurance company, a strategy can be adopted in which a sales person is dispatched preferentially to a promising customer while a relatively inexpensive sales channel such as direct mail is selected for other customers. In other words, the sales channel for the customer can be optimized. As described above, the analysis system 100 effectively supports the sales promotion activities by providing information on promising customers useful for the sales promotion activities of the company.

  The present invention has been described based on the embodiments. This embodiment is an exemplification, and it will be understood by those skilled in the art that various modifications can be made to combinations of the respective constituent elements and processing processes, and such modifications are also within the scope of the present invention. is there.

  In the above-described embodiment, a customer who lives in a high-profit area cluster and currently brings low profits to the company is presented as a promising customer. In the modified example, the area cluster specifying unit 34 compares the average revenue per customer of each area cluster, and among the plurality of area clusters, area clusters with relatively small profits obtained from the customers are referred to as “low profit area clusters”. May be specified. For example, an area cluster having an average profit per customer less than a predetermined rank may be set as a low profit area cluster. Further, an area cluster having an average profit per customer less than a predetermined value may be set as a low profit area cluster. Then, the customer extraction unit 36 selects a customer who has a relatively low profit among customers residing in an area belonging to the low-profit area cluster, and a customer who is unlikely to bring a profit larger than the current profit to the company in the future (expectation). It may be extracted as a thin customer). The analysis result output unit 38 provides the information presentation device 14 with information on the expected customer, and the information presentation device 14 presents the information on the expected customer to the user. According to this modified example, the sales person in the company can adopt a strategy that suppresses sales promotion activities for unexpected customers and selects a relatively inexpensive sales channel such as direct mail.

  Although not particularly mentioned in the above embodiment, the technical idea of the present invention is not limited to the extraction of promising customers from existing customers. In other words, the present invention can also be applied to the extraction of promising customers from potential customers (potential customers) that have not been traded with the company at the present time, in other words, that have not provided profits to the company. This potential customer includes, for example, the respondents of a questionnaire in which only the inhabited town chome and the contact information (address, telephone number, etc.) are known. In the analysis system 100, when the town chome where the potential customer resides belongs to the high profit area cluster, the potential customer is extracted as a promising customer. As described above, according to the analysis system 100, it is possible to select promising customers from a wide population including potential customers whose only residential streets are known.

  Moreover, in the said embodiment, although customer information DB10, the information analysis apparatus 12, and the information presentation apparatus 14 were demonstrated as another apparatus, of course, these functions may be performed in a single information processing apparatus. It is. The customer information DB 10 and the information presentation device 14 may be installed on the user company side, and the information analysis device 12 may be installed on the service provider side. In this case, the information analysis apparatus 12 receives the customer information via a communication network such as the Internet, and provides a service for transmitting information on the prospective customer to the user company. That is, a promising customer decision support service is provided as ASP / SaaS. When customer information is transmitted and received via a communication network such as the Internet, leakage of customer personal information can be a problem. However, as described above, the customer information required for the promising customer determination process in the information analysis device 12 is the customer ID, the customer address at the street level and the revenue information, and it is difficult to specify an individual. Personal information can also be protected.

  Any combination of the above-described embodiments and modifications is also useful as an embodiment of the present invention. The new embodiment generated by the combination has the effects of the combined embodiment and the modified examples.

  It should also be understood by those skilled in the art that the functions to be fulfilled by the constituent elements described in the claims are realized by the individual constituent elements shown in the embodiments and the modification examples or by their cooperation.

  DESCRIPTION OF SYMBOLS 10 Customer information DB, 12 Information analyzer, 14 Information presentation apparatus, 20 Area cluster information holding part, 32 Customer information acquisition part, 34 Area cluster specific part, 36 Customer extraction part, 38 Analysis result output part, 40 Promising customer, 100 Analysis system.

Claims (1)

An area cluster information holding unit that holds a correspondence relationship between each of a plurality of geographically partitioned areas and an area cluster obtained by grouping areas having similar attributes regarding residents;
A customer information holding unit that holds information about revenue obtained from each of a plurality of customers;
For each of the plurality of area clusters, an area cluster identifying unit that aggregates the revenues obtained from customers residing in each area cluster and identifies area clusters with relatively large revenues obtained from the customers;
Customer extraction that extracts customers with relatively small revenue among customers residing in the area cluster where the revenue is relatively large as customers who are likely to bring a larger revenue in the future than the currently obtained revenue And
An information analysis apparatus comprising:

Images