JP2017228056A - Information analyzer and information analyzing method - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a technology capable of supporting proper setting for a price of a merchandise.SOLUTION: An information analyzer 14 is configured to acquire area type data from an area type DB 10, and acquire IDPOS data from an IDPOS-DB 12. The information analyzer 14 is configured to derive, based on the acquired data, a price elastic value for each area type of a merchandise to be analyzed, the number of customers for each area type of a shop to be analyzed, and purchase frequency for each area type of a merchandise to be analyzed. The information analyzer 14 is configured to estimate, based on the derived data, sales quantity in a case of setting each of a plurality of sales prices for the merchandise to be analyzed in the shop to be analyzed.SELECTED DRAWING: Figure 1

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. The present applicant has proposed a technique for analyzing sales information of products and creating information for supporting the sales activities of users. Specifically, regarding the area where the purchaser of the product resides (hereinafter also referred to as “area”), paying attention to a group of areas with similar resident attributes (hereinafter also referred to as “area type”), the purchaser resides. A technique for creating information useful for merchandise sellers by analyzing sales information based on the area type is proposed (see, for example, Patent Document 1 and Patent Document 2).

JP 2009-169699 A JP 2011-211883 A

  The sales price of products may be set to the same price at any store in the country, and the price may be adjusted based on the intuition and experience of the store manager or the person in charge. It is not easy to set an optimal price that maximizes profits. This invention is made | formed in view of such a subject, The main objective is to provide the technique which assists setting the price of goods appropriately.

  In order to solve the above-described problem, an information analysis apparatus according to an aspect of the present invention includes a first acquisition unit that acquires area type data obtained by grouping a plurality of geographically partitioned areas into areas having similar resident attributes. And data indicating the store where the analysis target product was sold to the customer, the second acquisition unit for acquiring the sales price and sales quantity of the analysis target product in the store, and the sales performance data including the customer's residence area, and area type data Based on the sales performance data, the sales performance deriving unit for each area type for deriving the sales performance for each area type, and the sales results for each area type according to each of the multiple sales prices of the analysis target product A price elasticity value deriving unit that derives a price elasticity value for each area type of the product to be analyzed, and a sales quantity for each area type. Based on the actual number of customers who have purchased some products, based on the customer number deriving unit for deriving the number of purchased customers for each area type in the store to be analyzed and the sales results for each area type The purchase frequency deriving unit for deriving the purchase frequency indicating the purchase quantity for each area type of the analysis target product, the price elasticity value, the number of purchase customers, and the sales frequency of the analysis target product in the analysis target store based on the purchase frequency An estimation unit for estimating the sales quantity for each.

  Another embodiment of the present invention is also an information analysis device. The apparatus includes a first acquisition unit that acquires area type data obtained by grouping a plurality of geographically divided areas into areas having similar inhabitant attributes, data indicating a store that sells the analysis target product to a customer, Sales results for each area type based on the second acquisition unit that acquires the sales price and sales quantity of the products to be analyzed in the store and the sales result data including the customer's residence area, the area type data, and the sales result data Based on the sales results deriving section for each area type and the sales performance for each area type, the number of customers who have purchased some products, and the number of customers purchased for each area type in the store to be analyzed Purchasing analysis target products for each area type sold at a specified price based on the number of customers to be derived and sales results for each area type A purchase frequency deriving unit for deriving a purchase frequency indicating a quantity, an estimation unit for estimating a sales quantity when an analysis target product is sold at a predetermined price in an analysis target store based on the number of purchased customers and the purchase frequency; Prepare.

  Yet another embodiment of the present invention is an information analysis method. This method includes a step of acquiring area type data obtained by grouping a plurality of geographically divided areas into areas having similar inhabitant attributes, data indicating a store that sells the analysis target product to a customer, Acquiring sales price and sales quantity of the analysis target product and sales result data including the residential area of the customer; deriving sales result for each area type based on the area type data and the sales result data; Identifying a sales quantity corresponding to each of a plurality of sales prices of the analysis target product for each area type based on the sales performance for each area type, and deriving a price elasticity value for each area type of the analysis target product; Based on the sales results for each area type, the number of customers who have purchased some products A step of deriving the number of purchased customers for each area type in the store, a step of deriving a purchase frequency indicating a purchase quantity for each area type of the analysis target product based on a sales performance for each area type, a price elasticity value, The computer executes a step of estimating the sales quantity for each sales price of the analysis target product in the analysis target store based on the number of purchased customers and the purchase frequency.

  Note that any combination of the above-described constituent elements and a representation of the present invention converted between a system, a computer program, a recording medium storing the computer program, and the like are also effective as an aspect of the present invention.

  ADVANTAGE OF THE INVENTION According to this invention, it can support setting the price of goods appropriately.

It is a figure which shows the structure of the information processing system of 1st Example. It is a figure which shows the structure of area type data. It is a block diagram which shows the function structure of the information analyzer of FIG. It is a figure which shows the example of the price elasticity value data derived | led-out by the price elasticity value derivation | leading-out part. It is a figure which shows the example of the price elasticity value data derived | led-out by the price elasticity value derivation | leading-out part. It is a figure which shows the example of the customer number data derived | led-out by the customer number deriving part. It is a figure which shows the example of the purchase frequency data derived | led-out by the purchase frequency deriving part. It is a figure which shows the example of the estimation result by a sales quantity estimation part. It is a figure which shows the example of the estimation result by a sales estimation part. It is a figure which shows the example of the estimation result by a sales estimation part. It is a figure which shows the example of the estimation result by a gross profit estimation part. It is a figure which shows the example of the estimation result by a gross profit estimation part. It is a figure which shows the goods price optimization assistance model in 1st Example. It is a figure which shows the goods price optimization assistance model in 2nd Example.

Before describing the embodiment of the present invention, an outline will be described first.
Many retailers implement a loyalty program (such as a point program), and the purchaser may present a loyalty card (such as a point card) when purchasing the product. Along with this, in retailers and other information systems, POS data indicating the sales performance of products (data indicating what, when, where, how much, and how much) has been added to the buyer's information about who sold. The POS data with ID (hereinafter referred to as “IDPOS data”) may be accumulated, and the use of IDPOS data is being sought.

  In the following first and second embodiments, area type data in which each of a plurality of geographically partitioned areas is associated with an area type (also referred to as an area cluster) in which the areas are grouped, and IDPOS We propose a technology that supports optimal pricing for products by linking and analyzing data. The area type data can be said to be data indicating a correspondence relationship between a plurality of areas and a plurality of area types.

(First embodiment)
FIG. 1 shows a configuration of an information processing system 100 according to the first embodiment. The information processing system 100 includes an area type DB 10, an IDPOS-DB 12, an information analysis device 14, and a user terminal 16. These devices are connected via a communication network 18 including a LAN, a WAN, the Internet, and the like.

  The area type DB 10 is a database server that holds area type data. FIG. 2 shows a configuration of area type data held in the area type DB 10. In the “area type” column of the figure, area type identification information is set. In the “area” column, one or more areas belonging to the area type are set. For example, each of approximately 180,000 town-chomes in Japan may be set as an area and classified into any of about 50 area types. In the “population” column, the population of the area is set.

  In the “resident attribute” column, the resident attribute of the area type is set, and the resident attribute that is commonly applied to the areas belonging to the same area type is set. This resident attribute includes demographic attributes indicating demographic attribute data for each area type, and psychographic attributes indicating attribute data related to human psychology such as values and lifestyle of residents of each area type. 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”. In other words, the area type resident attribute is information indicating the image of consumers living in the area type, 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” column, a resident index value obtained by indexing the resident attributes of the area type is set. The resident index value is a plurality of types of index values obtained by indexing the degree of matching of area type resident attributes 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 type data will be described. The area type data 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 apparatus (not shown) that creates area type data may group 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. 1, the IDPOS-DB 12 is a database server that holds IDPOS data. The IDPOS data held in the IDPOS-DB 12 is data indicating sales results of a plurality of types of products at a plurality of stores. The IDPOS data includes data indicating a store where the product is sold to the customer (for example, store ID), data indicating the sold product (for example, product ID), the price of the sold product, and the customer who purchased the product. Living area (for example, data indicating a town street). The IDPOS data may include only the customer ID (for example, the point card ID) as the data of the customer who purchased the product. In this case, each customer's residence area may be held in another device or another table, and the customer's residence area may be specified (in other words, associated) by the customer's ID.

  The information analysis apparatus 14 sells a specific product to be analyzed (hereinafter referred to as “analysis target product”) at a specific retail store to be analyzed (hereinafter referred to as “analysis target store”). Data processing (for example, analysis processing, estimation processing, simulation) is performed to assist in appropriately setting the price. The analysis target store and the analysis target product may be specified from the user terminal 16.

  The user terminal 16 is an information terminal that instructs the information analysis apparatus 14 to start analysis processing in accordance with a user operation, and obtains an analysis result from the information analysis apparatus 14 and presents it to the user. The user terminal 16 may be a PC or a tablet terminal. Further, the user terminal 16 may be a web client device that accesses the information analysis device 14 via a web browser. In this case, the information analysis device 14 may have a function of a web server.

  FIG. 3 is a block diagram showing a functional configuration of the information analysis apparatus 14 of FIG. The information analysis device 14 includes a control unit 20, a storage unit 22, and a communication unit 24. The control unit 20 executes various data processing in the information analysis device 14. The storage unit 22 is a storage area that stores data that is referred to or updated by the control unit 20. The communication unit 24 communicates with an external device according to a predetermined communication protocol. The control unit 20 transmits and receives data to and from the area type DB 10, IDPOS-DB 12, and user terminal 16 via the communication unit 24.

  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 / memory of a computer or a mechanical device, and in terms of software, it can be realized by a computer program or the like. Then, 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, the function of each block of the control unit 20 may be implemented as a computer program, and the computer program may be installed in the storage of the information analysis device 14. Then, the function of each block of the control unit 20 may be exhibited by the CPU of the information analysis device 14 reading the computer program into the main memory and executing it. Each block of the storage unit 22 may be realized by storing data in a memory or storage of the information analysis device 14.

  The storage unit 22 includes an analysis result holding unit 26. The analysis result holding unit 26 holds data generated by each functional block of the control unit 20 described later.

  The control unit 20 includes an area type acquisition unit 28, an IDPOS acquisition unit 30, a sales performance derivation unit 32 by area type, a price elasticity derivation unit 34, a customer number derivation unit 36, a purchase frequency derivation unit 38, an estimation unit 40, and an analysis result. A providing unit 48 is included. The area type acquisition unit 28 acquires area type data from the area type DB 10. The IDPOS acquisition unit 30 acquires IDPOS data from the IDPOS-DB 12 as sales performance data. The sales result data acquired by the IDPOS acquisition unit 30 is recorded for each product sales fact. In other words, the sales result data is data for each sold product. Call.

  The area type acquisition unit 28 and the IDPOS acquisition unit 30 may acquire area type data and IDPOS data when the start of analysis processing is instructed from the user terminal 16. The area type acquisition unit 28 and the IDPOS acquisition unit 30 may acquire the entire area type data and IDPOS data in a lump. Alternatively, the area type acquisition unit 28 and the IDPOS acquisition unit 30 may acquire necessary portions of the area type data and the IDPOS data whenever necessary in the analysis processing in the information analysis device 14. Note that acquiring data includes referring to the data and reading the data into the memory.

  In the embodiment, the area type data and the IDPOS data are held in the area type DB 10 and IDPOS-DB 12 different from the information analysis device 14, but at least one of the area type data and the IDPOS data is a storage unit of the information analysis device 14. 22 may be held. In that case, the area type acquisition unit 28 and the IDPOS acquisition unit 30 may read the area type data and IDPOS data held in the storage unit 22 into the memory.

  When the IDPOS data includes the customer ID but does not include the customer residence area information, the IDPOS acquisition unit 30 holds the customer attribute information (information indicating the residence area such as an address) after acquiring the IDPOS data from the IDPOS-DB 12. Other devices may be accessed. And IDPOS acquisition part 30 may acquire a customer's residence area information from the other device by using customer ID as a key. In any case, the IDPOS acquisition unit 30 acquires sales performance data including the store where the product is sold to the customer, the sales price of the product, and the customer's residence area.

  In the present embodiment, the sales data for each product acquired by the IDPOS acquisition unit 30 is IDPOS data related to a plurality of types of products sold at a plurality of stores. As a modification, the IDPOS acquisition unit 30 includes at least data indicating a store that sold the analysis target product to a customer among a plurality of stores in which the IDPOS data is recorded, and the sales price and sales quantity of the analysis target product (especially the analysis target). What is necessary is just to acquire the sales result data according to goods (namely, a part of IDPOS data) including the residence area of the customer who purchased the analysis object goods). For example, when an analysis target product is designated from the user terminal 16, the IDPOS acquisition unit 30 may acquire only IDPOS data related to the analysis target product from the IDPOS-DB 12.

  Based on the area type data acquired by the area type acquisition unit 28 and the sales result data by product acquired by the IDPOS acquisition unit 30, the sales result deriving unit 32 by area type (hereinafter referred to as the sales results for each area type). Derived as “Sales data by area type”). The sales record deriving unit 32 by area type stores the derived sales record data by area type in the analysis result holding unit 26.

  For example, the sales record deriving unit 32 by area type refers to the area type data, and for each record of the sales record data by product, the area type corresponding to the residential area of the customer included in each record is set in each record. By adding, sales result data for each product may be converted into sales result data for each area type. The sales record deriving unit 32 by area type groups the sales records by area type by grouping a plurality of records of the sales record data by product for each area type corresponding to the residential area of the customer included in each record. It may be generated.

  The price elasticity value deriving unit 34 calculates, for each area type, the sales quantity corresponding to each of a plurality of sales prices of the analysis target product based on the sales performance data by area type derived by the sales performance deriving unit 32 by area type. Identify and derive the price elasticity for each area type of the analysis target product. The price elasticity value deriving unit 34 stores price elasticity value data indicating the price elasticity value for each area type of the analysis target product in the analysis result holding unit 26.

  For example, the price elasticity value deriving unit 34 extracts (1) records related to sales of the analysis target product from the records of sales performance data by area type, and (2) extracts the extracted records for each combination of area type and sales price. (3) The sales quantities indicated by the records of each group may be totaled to derive the sales quantity for each combination of area type and sales price. Then, the price elasticity value deriving unit 34 may derive a ratio between the sales quantity at a predetermined reference price and the sales quantity at a price different from the reference price as a price elasticity value.

  FIG. 4 shows an example of price elasticity value data derived by the price elasticity value deriving unit 34. This figure shows price elasticity value data of each area type when 140 yen is set as a reference price for a certain analysis target product (for example, a specific product of a 500 ml plastic bottle beverage designated by the user). The price elasticity value data in the figure shows that the sales quantity (ratio) increases as the selling price decreases, and the sales quantity (ratio) decreases as the selling price increases. The reference price may be specified on the user terminal 16 or may be determined in advance in product units or product category units.

  The price elasticity value deriving unit 34 may derive a function (regression equation, graph, approximate curve, etc.) with the selling price as a variable as price elasticity value data for each area type. FIG. 5 shows an example of price elasticity value data derived by the price elasticity value deriving unit 34. This figure shows price elasticity value data (graph) in an area type when 140 yen is a base price for a certain analysis target product. In other words, a regression curve is shown in which the sales price of the analysis target product is an explanatory variable and the sales volume ratio of the analysis target product is an objective variable. As in FIG. 4, FIG. 5 also shows that the sales quantity (ratio) increases as the selling price decreases, and the sales quantity (ratio) decreases as the selling price increases.

  The price elasticity value deriving unit 34 compares the sales quantity at a predetermined reference price with the sales quantity at a price different from the reference price, and calculates the sales quantity at each price at each price. Normalization may be performed by the number of stores that sell the analysis target product, and the ratio of the sales volume after normalization may be derived as a price elasticity value. For example, the sales volume at a given base price is divided by the number of stores sold at that base price, and the sales volume at a price different from the base price is divided by the number of stores sold at that different price. The ratio may be derived as a price elasticity value. Further, the price elasticity value deriving unit 34 may derive, as a price elasticity value, a ratio between the average sales quantity at each store at a predetermined reference price and the average sales quantity at a price different from the reference price. According to this aspect, it is possible to increase the accuracy of the price elasticity value by filling the difference in the number of stores adopting each selling price.

  Returning to FIG. 3, the customer number deriving unit 36 is the number of customers in a predetermined analysis target store among a plurality of stores based on the sales record data by area type derived by the sales result deriving unit 32 by area type. Deriving the number of customers residing in each of the multiple area types. Hereinafter, a customer who purchases some product at a plurality of stores including the analysis target store (that is, a customer in which the fact of product purchase is recorded in the IDPOS) is also referred to as a “purchased customer”. The customer number deriving unit 36 derives the number of purchased customers for each area type in the analysis target store.

  For example, the number-of-customers deriving unit 36 extracts (1) a record in which sales fact data of a product at an analysis target store is recorded from among records of sales performance data by area, and (2) extracts the extracted record for each area type. They may be grouped into groups. (3) The number of records belonging to each group (in other words, the number of purchased customers) may be counted to derive the number of purchased customers for each area type.

  The customer number deriving unit 36 stores customer number data indicating the number of customers for each area type of the analysis target store in the analysis result holding unit 26. FIG. 6 shows an example of customer number data derived by the customer number deriving unit 36. In the example of FIG. 6, customers of the analysis target store exist in any of the 30 area types, but depending on the store, there may be zero customers residing in a specific area type.

  Returning to FIG. 3, the purchase frequency deriving unit 38 derives the purchase frequency indicating the purchase quantity for each area type of the analysis target product based on the sales result data by area type derived by the sales result deriving unit 32 by area type. To do. Specifically, the sales record deriving unit 32 by area type derives, for each area type, the purchase frequency indicating the purchase quantity of the analysis target product per purchase customer who purchased some product. The purchase quantity can be said to be the sales quantity when viewed from the store. The purchase frequency can also be said to be the probability that a customer who purchases some product at any of a plurality of stores will purchase the analysis target product. In the present embodiment, the purchase frequency (based on all stores) is derived for the purchase customers of all stores that are tabulated in the sales performance data by area type. As a modification, the purchase frequency deriving unit 38 may derive the purchase frequency (individual store base) for the purchase customers of the analysis target store.

  The purchase frequency deriving unit 38 stores purchase frequency data indicating the purchase frequency for each area type of the analysis target product in the area type acquiring unit 28. FIG. 7 shows an example of purchase frequency data derived by the purchase frequency deriving unit 38. For example, the purchase frequency deriving unit 38 calculates the purchase quantity (in other words, the sales quantity) of the analysis target product in each area type from the record of each area type in the sales performance data by area type, and the purchase customer in each area type. The number (in other words, the number of records in which the purchase fact of some product is recorded) may be calculated. Then, the purchase frequency deriving unit 38 may derive the purchase frequency in each area type by obtaining the ratio between the purchase quantity of the analysis target product in each area type and the number of purchased customers in each area type.

  The purchase frequency deriving unit 38 of the present embodiment derives a purchase frequency (that is, a reference price-based purchase frequency) indicating a purchase quantity for each area type of the analysis target product sold at a predetermined reference price. The reference price may be specified on the user terminal 16 or may be determined in advance in product units or product category units. Specifically, the purchase frequency deriving unit 38 derives, for each area type, a purchase frequency indicating the purchase quantity per purchase customer of the analysis target product sold at a predetermined reference price.

  For example, the purchase frequency deriving unit 38 calculates the purchase quantity of the analysis target product (however, a reference price is set) in each area type based on the record of each area type in the sales performance data by area type, The number of purchased customers in each area type may be calculated. Then, the purchase frequency deriving unit 38 derives the purchase frequency based on the reference price in each area type by obtaining the ratio between the purchase quantity of the analysis target product in each area type and the number of purchased customers in each area type. Good. In the purchase frequency data of FIG. 7, the average sales quantity (average purchase quantity) as a result of the purchase customer residing in the area type “Type1” across multiple stores purchasing the analysis target product sold at a predetermined reference price. ) Is calculated as “0.19”. More specifically, when the product of the purchase customer and the number of visits reaches 5 (for example, when 5 purchase customers come to the store once), one analysis target product with a predetermined reference price is purchased. ing.

  Returning to FIG. 3, the estimating unit 40 calculates the price elasticity value for each area type of the analysis target product derived by the price elasticity value deriving unit 34 and the area type of each analysis target store derived by the customer number deriving unit 36. Based on the number of customers and the purchase frequency for each area type of the analysis target product derived by the purchase frequency deriving unit 38, information on the sales of the analysis target product in the analysis target store is estimated. In other words, information for supporting the sale of the analysis target product in the analysis target store is generated. The estimation unit 40 includes a sales quantity estimation unit 42, a sales estimation unit 44, and a gross profit estimation unit 46.

  The sales quantity estimation unit 42 is the sales quantity of the analysis target product in the analysis target store, and estimates the sales quantity when each of a plurality of sales prices is set for the analysis target product. For example, the sales quantity estimation unit 42 (1) the number of customers for each area type of the analysis target store derived by the customer number deriving unit 36 and the area type of the analysis target product derived by the purchase frequency deriving unit 38 Based on the purchase frequency (based on the reference price), the sales quantity when the analysis target product is sold at the reference price in the analysis target store may be estimated. Based on the price elasticity value for each area type of the analysis target product derived by the price elasticity value deriving unit 34, the sales quantity estimation unit 42 sets the analysis target product at a price different from the reference price at the analysis target store. The sales quantity may be estimated when selling at.

  FIG. 8 shows an example of an estimation result by the sales quantity estimation unit 42. The sales quantity estimation unit 42 sells the analysis target product at the analysis target store at the reference price by multiplying the number of customers of the analysis target store by the purchase frequency of the analysis target product for each area type as the process of (1) above. In this case, the sales quantity may be calculated for each area type. In FIG. 8, the sales price column of 140 yen corresponds. In addition, as the processing of (2) above, the sales quantity estimation unit 42 multiplies the sales quantity at the standard price by the price elasticity value for each area type, so that the analysis target product is set at the analysis target store other than the standard price. You may calculate the sales quantity at the time of selling for every area type. In FIG. 8, the column (135 yen, 145 yen, etc.) other than the sales price of 140 yen corresponds. The unit of the values in the table of FIG. 8 is “pieces”.

  The sales quantity estimation unit 42 is an estimation result of the sales quantity corresponding to each of a plurality of sales prices. For example, an estimated value of the sales quantity for each area type and an estimated value of the total sales quantity for each sales price. Is stored in the analysis result holding unit 26. For example, the data shown in FIG. 8 may be stored in the analysis result holding unit 26.

  Returning to FIG. 3, the sales estimation unit 44 is an estimation result by the sales quantity estimation unit 42, and calculates each of the plurality of sales prices based on the estimated value of the sales quantity when each of the plurality of sales prices is set. Estimate the sales amount when set. For example, the sales estimation unit 44 uses a plurality of area types (30 types in the present embodiment) when the analysis target product is sold at a certain price (referred to herein as “unit price A”) at the analysis target store. The result of multiplying the total sales volume by unit price A may be calculated as sales when the analysis target product is sold at unit price A. This calculation may be repeated for a plurality of sales prices, and the sales corresponding to each of the sales prices may be calculated.

  FIG. 9 shows an example of an estimation result by the sales amount estimation unit 44. In the figure, the sales for each area type (unit: 1,000 yen) when the selling price of the analysis target product is set to 100 to 180 yen are shown. Further, the lowermost part of the figure shows the total value of sales over 30 area types at each selling price. FIG. 10 also shows an example of an estimation result by the sales amount estimation unit 44. The graph of FIG. 10 shows the transition of the total sales value accompanying the change in the selling price shown in FIG.

  The sales estimation unit 44 is an estimation result of sales corresponding to each of a plurality of sales prices. For example, an estimated value of sales for each area type and an estimated value of total sales for each sales price are obtained. The result is stored in the analysis result holding unit 26. For example, the data shown in FIG. 9 or 10 may be stored in the analysis result holding unit 26.

  Returning to FIG. 3, the gross profit estimation unit 46 is an estimation result by the sales quantity estimation unit 42 and the sales amount estimation unit 44, and the sales quantity and the sales when each of a plurality of sales prices is set for the analysis target product. Based on the estimated value of high, the magnitude of profit when each of a plurality of sales prices is set is estimated. In this embodiment, the gross profit due to the sale of the analysis target product in the analysis target store is estimated. For example, the gross profit estimation unit 46 calculates the cost from the sales amount (that is, unit price A × sales quantity) when the analysis target product of the cost a is sold at a certain price (herein referred to as “unit price A”) in the analysis target store. The result of subtracting (ie, cost a × sales quantity) may be calculated as a gross profit when the analysis target product is sold at unit price A. This calculation may be repeated for a plurality of patterns of sales prices, and the gross profit corresponding to each of the plurality of sales prices may be calculated.

  FIG. 11 shows an example of an estimation result by the gross profit estimation unit 46. The figure shows the gross profit (unit: 1,000 yen) for each area type when the selling price of the analysis target product is set to 100 to 180 yen. In the lowermost part of the figure, the total value of gross profit over 30 area types at each selling price is shown. FIG. 12 also shows an example of an estimation result by the sales amount estimation unit 44. The graph of FIG. 12 shows the transition of the gross profit total value accompanying the change in the selling price shown in FIG.

  The gross profit estimation unit 46 is an estimation result of gross profit corresponding to each of a plurality of sales prices. For example, an estimated value of gross profit for each sales price for each area type and an estimated value of total gross profit for each sales price. Is stored in the analysis result holding unit 26. For example, the data shown in FIG. 11 or 12 may be stored in the analysis result holding unit 26.

  Returning to FIG. 3, when the analysis result providing unit 48 receives the data requesting the provision of the analysis result from the user terminal 16, the analysis result providing unit 48 sends the analysis result data stored in the analysis result holding unit 26 to the user terminal 16. Send. For example, the sales quantity estimation result by the sales quantity estimation unit 42 (FIG. 8), the sales estimation result by the sales estimation unit 44 (FIGS. 9 and 10), and the gross profit estimation result by the gross profit estimation unit 46 (FIG. 11, FIG. 12) may be provided to the user terminal 16. Further, the price elasticity value (FIGS. 4 and 5), the number of customers (FIG. 6), and the purchase frequency (FIG. 7) may be provided to the user terminal 16. The analysis result providing unit 48 may collectively provide data of a plurality of types of analysis results to the user terminal 16 and provide only the types of analysis results specified in the analysis result provision request to the user terminal 16. Also good.

The operation of the information processing system 100 configured as above will be described below.
First, the user inputs the identification information of the analysis target store, the identification information of the analysis target product, and the cost of the analysis target product to the user terminal 16, and the user terminal 16 sends an analysis request specifying these parameters to the information analysis device 14. Send. As an option, the reference price of the analysis target product may be further specified. When receiving the analysis target request from the user terminal 16, the information analysis apparatus 14 executes the analysis process shown in FIG. FIG. 13 shows a product price optimization support model that schematically shows an analysis process performed by the information analysis apparatus 14 according to the first embodiment.

  The IDPOS acquisition unit 30 of the information analysis apparatus 14 acquires IDPOS data from the IDPOS-DB 12 as sales data for each product (S10). The area type acquisition unit 28 of the information analyzer 14 acquires area type data from the area type DB 10 (S12). The sales record deriving unit 32 by area type of the information analyzer 14 generates sales record data by area type based on the data acquired in S10 and S12 (S14). Based on the sales results data by area type, the price elasticity value deriving unit 34 of the information analysis device 14 derives the price elasticity value by area type for the analysis target product (S16), and the customer number deriving unit 36 performs analysis. The number of customers by area type for the target store is derived (S18), and the purchase frequency deriving unit 38 derives the purchase frequency by area type for the analysis target product (S20).

  Based on the data derived in S16 to S20, the sales quantity estimation unit 42 of the information analysis device 14 is expected sales for each of a plurality of sales prices when the analysis target product is sold at the analysis target store. The quantity is estimated (S22). The sales estimation unit 44 estimates the sales amount expected for each of a plurality of sales prices when the analysis target product is sold at the analysis target store based on the sales quantity estimated in S22 (S24). ). Based on the data estimated in S22 and S24, the gross profit estimation unit 46 estimates the gross profit expected for each of a plurality of sales prices when the analysis target product is sold at the analysis target store ( S26).

  The user terminal 16 transmits a request for providing various analysis results by the information analysis device 14 to the information analysis device 14 in accordance with a user operation. The analysis result providing unit 48 of the information analyzer 14 transmits data of various analysis results held in the analysis result holding unit 26 to the user terminal 16. The user terminal 16 displays the analysis result data received from the information analysis device 14 on a predetermined display device.

  The information analysis device 14 may be connected to an input device (not shown) such as a keyboard or a mouse and a display device (not shown). In this case, the information analysis device 14 may further include an operation acquisition unit and a display control unit. The operation acquisition unit acquires an operation input from the input device, and the information analysis device 14 may execute an analysis process in accordance with parameters (analysis target product, analysis target store, etc.) designated by the operation. . The display control unit may display the analysis result held in the analysis result holding unit 26 on the display device in accordance with an operation input from the input device.

  According to the information analysis apparatus 14 of the first embodiment, the price of the product is set so that the sales quantity, sales, or gross profit can be maximized in accordance with the different trade area characteristics (in other words, the characteristics of the customer who visits the store). Can support. Moreover, although the store visits (in other words, customer attributes) differ depending on the location and brand of the store, the information analysis apparatus 14 can support the implementation of optimal price settings according to such store visits.

  Furthermore, according to the information analysis device 14, it is possible to estimate the sales quantity, the sales amount, or the gross profit in the price range where there is no sales record in the analysis target store. For example, with respect to the sales estimation result of FIG. 9, even if there is no sales performance at a price of 100 yen to 120 yen and 150 yen to 180 yen in the analysis target store, the sales performance of other stores is reflected through the area type. Thus, sales can be estimated even for a price range where there is no sales record. Furthermore, for products that do not have sales results at the stores subject to analysis (in other words, there is no handling results), the sales results of other stores are reflected through the area type, so that the sales volume and sales of products that do not have sales results are also reflected. High or gross margin can be estimated.

(Second embodiment)
In the first embodiment, the sales quantity at the base price is estimated based on the number of customers for each area type for the analysis target store and the purchase frequency (base price base) for each area type for the analysis target product, Based on the price elasticity, the sales volume at a price other than the base price was estimated. In the second embodiment, up to the process of estimating information related to sales at the base price based on the number of customers for each area type for the analysis target store and the purchase frequency (base price base) for each area type for the analysis target product Execute.

  The configuration of the information processing system 100 of the second embodiment is the same as that of the first embodiment (FIG. 1), and the configuration of the information analysis apparatus 14 of the second embodiment is also the same as that of the first embodiment (FIG. 3). However, the information analyzer 14 of the second embodiment differs from the first embodiment in that the price elasticity value deriving unit 34 is not provided. Hereinafter, differences from the first embodiment will be mainly described.

  FIG. 14 shows a product price optimization support model that schematically shows an analysis process performed by the information analysis apparatus 14 according to the second embodiment. S30 to S38 in the figure are the same as S10 to S14, S18, and S20 in FIG. The sales quantity estimation unit 42 calculates the number of customers for each area type of the analysis target store derived by the customer number deriving unit 36 and the purchase frequency (reference price) for each area type of the analysis target product derived by the purchase frequency deriving unit 38. Based on the base), the sales quantity when the analysis target product is sold at the base price in the analysis target store is estimated (S40). The reference price is the selling price of the analysis target product used to derive the purchase frequency.

  The sales estimation unit 44 is an estimation result of the sales quantity estimation unit 42, and based on the estimated value of the sales quantity when the reference price is set for the analysis target product, the analysis target product when the reference price is set Sales are estimated (S42). The gross profit estimator 46 is an estimation result by the sales quantity estimator 42 and the sales amount estimator 44. Based on the sales quantity and the estimated sales amount when the reference price is set for the analysis target product, The gross profit at the time of selling the analysis target product for which the reference price is set is estimated (S44). That is, in the second embodiment, only the analysis result (for example, data in the column of 140 yen) related to the base price among the analysis results shown in FIGS. 8 to 12 is generated.

  In the second embodiment, the user may further input a reference price of the analysis target product, and the user terminal 16 may transmit an analysis request further specifying the reference price of the analysis target product to the information analysis device 14. The user can obtain an analysis result (estimated value of sales volume, sales amount, gross profit) based on each of a plurality of types of reference prices by making an analysis request a plurality of times while changing the reference price.

  The present invention has been described based on the first embodiment and the second embodiment. It is to be understood by those skilled in the art that these embodiments are exemplifications, and that various modifications can be made to combinations of each component and each processing process, and such modifications are also within the scope of the present invention.

  A modification of the first embodiment will be described. The price elasticity value deriving unit 34 may derive the price elasticity value for each area type of the analysis target product based on the sales performance for each area type in the analysis target period corresponding to a predetermined annual event or season. That is, the price elasticity value in the analysis target period may be derived. For example, the user may input an analysis target period corresponding to a predetermined yearly event or season, and the user terminal 16 may transmit an analysis request specifying the input analysis target period to the information analysis apparatus 14. As the analysis target period, an arbitrary period ranging from one week to several months may be specified. For example, a period from December 1 to December 25 may be designated as a period corresponding to the event “Christmas”. In addition, a period from June 1 to August 31 may be designated as a period corresponding to the season “summer”.

  The sales date of the analysis target product is recorded in the IDPOS data, and the sales data by area type based on the IDPOS data also includes the sales date. The price elasticity value deriving unit 34 extracts a record whose sales date is included in the analysis target period from the plurality of records of the sales performance data by area type, and based on the extracted record, the price elasticity value for the analysis target product Data may be generated. As described above, the analysis target period may be specified by the user terminal 16, and the most recent period for each analysis target product (or product category) is determined in advance. Also good. According to this modification, since the price elasticity value in consideration of annual events and seasonality is derived, it is possible to further increase the accuracy of estimation of sales volume, sales amount, or gross profit.

  A modification of the first embodiment and the second embodiment will be described. Together with the price elasticity value deriving unit 34 of the above modification or instead of the price elasticity value deriving unit 34 of the above modification, the purchase frequency deriving unit 38 is an area type in an analysis target period corresponding to a predetermined annual event or season. You may derive | lead-out the purchasing frequency for every area type of analysis object goods based on the sales performance for every. That is, the purchase frequency of the analysis target product in the analysis target period may be derived. The purchase frequency deriving unit 38 extracts a record whose sales date is included in the analysis target period from the plurality of records of the sales record data by area type, and obtains the purchase frequency data for the analysis target product based on the extracted record. It may be generated. Thereby, since the purchase frequency in consideration of annual events and seasonality is derived, it is possible to further improve the accuracy of estimation of sales volume, sales, or gross profit.

  A modification of the first embodiment and the second embodiment will be described. The purchase frequency deriving unit 38 sets the area type as the purchase frequency (also referred to as purchase probability) based on the sales performance data by area type, and the ratio of customers who have purchased the analysis target product to the purchase customers who have purchased some products. You may derive for every. For example, the purchase frequency deriving unit 38 obtains the ratio of the number of customers who have purchased the analysis target product in the total number of purchased customers from the record of each area type of the sales performance data by area type, thereby obtaining the purchase frequency of each area type. May be derived. In addition, the purchase frequency deriving unit 38 may derive the ratio of records indicating that the analysis target product has been purchased, which occupies the total number of records of each area type, as the purchase frequency of each area type. Further, the purchase frequency deriving unit 38 sets, as the purchase frequency (also referred to as purchase probability), the ratio of the customers who have purchased the analysis target products sold at a predetermined reference price to the purchase customers based on the sales results data by area type. You may derive for every area type. The sales quantity, sales amount, or gross profit can also be estimated based on the purchase frequency of this modification.

  The product to be analyzed by the information analysis device 14 may be not only a tangible object but also an intangible object that a customer pays for and purchases. For example, the product to be analyzed by the information analysis device 14 may include a service (service).

  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.

  14 information analysis device, 28 area type acquisition unit, 30 IDPOS acquisition unit, 32 sales result deriving unit by area type, 34 price elasticity value deriving unit, 36 customer number deriving unit, 38 purchase frequency deriving unit, 40 estimating unit, 100 information Processing system.

Claims (7)

A first acquisition unit that acquires area type data obtained by grouping a plurality of geographically divided areas into areas having similar inhabitant attributes;
Data indicating a store where the analysis target product is sold to a customer; a second acquisition unit that acquires sales performance data including a sales price and a sales quantity of the analysis target product in the store; and a residence area of the customer;
Based on the area type data and the sales performance data, a sales performance derivation unit by area type for deriving a sales performance for each area type,
Based on the sales performance for each area type, the sales quantity corresponding to each of the plurality of sales prices of the analysis target product is specified for each area type, and the price elasticity value for each area type of the analysis target product is derived. Price elasticity value deriving section;
A customer number deriving unit for deriving the number of purchased customers for each area type in the analysis target store, based on the sales results for each area type, the number of purchased customers who are customers who have purchased some product,
A purchase frequency deriving unit for deriving a purchase frequency indicating a purchase quantity for each area type of the analysis target product based on the sales performance for each area type;
Based on the price elasticity value, the number of purchased customers, and the purchase frequency, an estimation unit that estimates a sales quantity for each sales price of the analysis target product in the analysis target store;
An information analysis apparatus comprising: The purchase frequency deriving unit derives a purchase frequency indicating a purchase quantity for each area type of the analysis target product sold at a predetermined reference price,
The estimation unit estimates a sales quantity when the analysis target product is sold at the reference price in the analysis target store based on the number of purchased customers and the purchase frequency, and further based on the price elasticity value The information analysis apparatus according to claim 1, wherein a sales quantity is estimated when the analysis target product is sold at a price different from the reference price in the analysis target store.   The information analysis apparatus according to claim 1, wherein the estimation unit further estimates a sales amount for each sales price based on an estimated value of a sales quantity for each sales price.   The price elasticity value deriving unit derives a price elasticity value for each area type of the analysis target product based on a sales performance for each area type in an analysis target period corresponding to a predetermined annual event or season. The information analysis apparatus according to any one of claims 1 to 3. A first acquisition unit that acquires area type data obtained by grouping a plurality of geographically divided areas into areas having similar inhabitant attributes;
Data indicating a store where the analysis target product is sold to a customer; a second acquisition unit that acquires sales performance data including a sales price and a sales quantity of the analysis target product in the store; and a residence area of the customer;
Based on the area type data and the sales performance data, a sales performance derivation unit by area type for deriving a sales performance for each area type,
A customer number deriving unit for deriving the number of purchased customers for each area type in the analysis target store, based on the sales results for each area type, the number of purchased customers who are customers who have purchased some product,
A purchase frequency deriving unit for deriving a purchase frequency indicating a purchase quantity for each area type of the analysis target product sold at a predetermined price based on the sales results for each area type;
An estimation unit that estimates a sales quantity when the analysis target product is sold at the predetermined price in the analysis target store based on the number of purchased customers and the purchase frequency;
An information analysis apparatus comprising: Obtaining area type data obtained by grouping a plurality of geographically divided areas into areas having similar inhabitants attributes;
Data indicating a store where the analysis target product is sold to a customer, a sales price and a sales quantity of the analysis target product in the store, and obtaining sales result data including a residence area of the customer;
Deriving the sales performance for each area type based on the area type data and the sales performance data;
Based on the sales performance for each area type, the sales quantity corresponding to each of the plurality of sales prices of the analysis target product is specified for each area type, and the price elasticity value for each area type of the analysis target product is derived. Steps,
Deriving the number of purchased customers who are customers who have purchased some products based on the sales performance for each area type, and deriving the number of purchased customers for each area type in the analysis target store;
Deriving a purchase frequency indicating a purchase quantity for each area type of the analysis target product based on sales results for each area type;
Estimating a sales quantity for each sales price of the analysis target product in the analysis target store based on the price elasticity value, the number of purchased customers, and the purchase frequency;
A computer-executable information analysis method. A function to obtain area type data by grouping multiple geographically divided areas into areas with similar inhabitants attributes,
Data indicating a store that sells the analysis target product to a customer, a function of acquiring sales result data including a sales price and a sales quantity of the analysis target product in the store, and a residence area of the customer;
Based on the area type data and the sales performance data, a function for deriving the sales performance for each area type,
Based on the sales performance for each area type, the sales quantity corresponding to each of the plurality of sales prices of the analysis target product is specified for each area type, and the price elasticity value for each area type of the analysis target product is derived. Function and
Based on the sales results for each area type, the number of purchasing customers who are customers who have purchased some product, a function of deriving the number of purchasing customers for each area type in the analysis target store,
A function of deriving a purchase frequency indicating a purchase quantity for each area type of the analysis target product based on a sales performance for each area type;
A function of estimating a sales quantity for each selling price of the analysis target product in the analysis target store based on the price elasticity value, the number of purchased customers, and the purchase frequency;
A computer program for realizing a computer.

Images