KR100986624B1 - Method and system for estimate potential market area and forecast market revenue - Google Patents

Abstract

PURPOSE: A sale prediction, a prediction generation method and a system thereof by utilizing a cell statistics technique are provided to generate predicted sales and predicted area by setting a boundary of the region in which the sale generation is expected in a cell form. CONSTITUTION: A cell generating unit(120) generates a plurality of cells. A cell information operator(130) generates a result table including the society of humanity information. A shop location information designator(140) designs the location of the race store. A competition information calculator(150) includes a rival shop distance into the result table.

Description

Revenue forecasting and forecasting business area generation method and system using cell statistics technique {Method and System for Estimate Potential Market Area and Forecast Market Revenue}

The present invention relates to a method and system for generating revenue forecasting and predictive trade zone using a cell statistics technique for predicting a regional sales and a trade zone for a given store using a cell statistics technique.

In recent years, there have been many attempts to apply GIS in the private sector, and some challenging companies have been using GIS for many years to make major decisions and increasing the utilization of GIS every year.

In addition, in the highly competitive domestic discount store market, many studies have been conducted to solve the management tasks of companies that wish to secure fundamental competitiveness through the introduction of GIS. These companies are not satisfied with grasping regional characteristics. It demands solutions on what strategies to establish in each region, and expects to create new demand.

Increasing sales is a key management goal for all companies, and considering this, sales forecasting using GIS is significant for companies. In particular, companies that operate stores such as department stores and discount stores require sales forecasts using GIS as a tool to support objective management strategies.

On the other hand, in the case of the sales forecasting method using the existing GIS, the process of estimating the sales by statistical methods by extracting the humanities and social statistical data within a certain radius. This can be judged as an efficient way of diagnosing the present based on past information, but there is no practical solution because there is no clear solution on how to prepare future sales targets. have. For this reason, the existing sales forecasting method using GIS has a problem that even if the statistical explanatory power of prediction is high, it cannot be properly used in field work of companies.

Accordingly, the present invention has been made to solve the above-mentioned conventional problems, and the object thereof is to set the boundary of the region where sales are expected to be generated in a cell form, and to use the statistical technique for each cell to estimate the sales revenue and The present invention provides a method and system for generating revenue forecasting and forecasting business area using cell statistics to generate an expected sales area.

According to the method of the present invention to achieve the above object, the step of generating a plurality of cells having a predetermined size around the location of a specific expected store in the cell generation unit, the cell information calculation unit for each cell around the expected store Generating a result table containing the humanities and social information for each cell by applying the humanities and social information of the region, and calculating by applying the humanities and social information in the result table to the regression equation as a variable value in the commercial prediction unit And predicting the expected sales by each cell and the number of customer visits, and generating an expected sales area around the estimated store by using the estimated sales and the number of customer visits predicted by each cell. The present invention provides a method of generating revenue forecasting and forecasting commercial zones using cell statistics.

According to the system of the present invention for achieving the above object, a cell generation unit for generating a plurality of cells having a predetermined size around the position of a specific expected store, and each cell around the expected store generated by the cell generation unit Cell information operation unit that generates a result table containing humanities and social information for each cell by applying the humanities and social information of each region, and estimates for each cell by calculating and applying the humanities and social information of the result table as variable values A commercial area predictor for predicting sales, the number of visits to customers, and a commercial area for generating an estimated sales area centered on the expected store by using the estimated sales predicted by each cell by the commercial area predictor and the number of customer visits. Provides a sales forecasting and forecasting business zone generation system using a cell statistics method characterized in that it comprises a calculation unit The.

As described above, according to the present invention, statistical analysis of sales and humanities and social information is performed by matching customer information and humanities and social information which are constructed based on point data to cells separated by a predetermined distance unit, and are derived through statistical analysis. By using the regression formula to calculate the possible rate of customization for each cell, it is possible to calculate the expected business information, that is, the expected sales and the expected sales area for the store that is expected to enter or the store that is currently in store. When developing a store, it is possible not only to grasp the expected sales of the store, but also to predict the size and shape of the commercial area to be formed in the future, which can be usefully used as a strategic data for establishing a marketing strategy. In this case, we can find new areas where sales can be increased by comparing the actual sales region and forecasted sales characteristics by region. It can be usefully used in establishing a marketing strategy.

Hereinafter, the present invention configured as described above will be described in detail with reference to the accompanying drawings.

That is, Figure 1 is a diagram showing the overall configuration for the sales forecasting and predictive commercial area generation system using the cell statistics technique according to the present invention.

As shown in FIG. 1, the sales prediction and prediction commercial zone generation system using the cell statistical method according to the present invention includes a regression generation unit 100, a customer information database 200, a humanities and social information database 300, The prediction commercial area information generation unit 400 is configured.

The regression generation unit 100 receives a point value (X, Y) of a specific main store that is a reference for generating a regression equation, and sets a predetermined size within a predetermined radius based on the location information of the main store generated on the electronic map. Generates a plurality of cells (Cell) having, and the customer information and humanities and social information for each cell through the customer information of the customer information database 200 and the population information of the population distribution of the corresponding region of the humanities and social information database 300 By calculating the customer information and humanities and social information of each cell by using the competitive information with the competitive store, the regression equation is derived by performing statistical analysis using the constructed information of each cell Done.

The customer information database 200 stores customer sales information, customer visit frequency information, etc. for the customers owned by the store or the company and the company, and the database configuration is shown in Table 1 below. As shown.

       Customer address  X (location information)  Y (location information)  take  Visits  Yeoksam 1-dong, Gangnam-gu, Seoul ...       304499       509173  1309287        10  Yeoksam 2-dong, Gangnam-gu, Seoul ...       309633       503173    23000         3  Yeoksam 3-dong, Gangnam-gu, Seoul ...       309173       509633    10000         One .
.
. .
.
. .
.
. .
.
. .
.
.

Here, (X, Y), which is location information of the customer information database 200, can be given as a coordinate value on a map using address information of each customer.

The humanities and social information database 300 stores the humanities and social information about the general area where the store can enter, that is, the total number of households, the number of apartments, etc. for each location of the population distribution area, the database configuration is As shown in Table 2 below.

   X (location information)    Y (location information)     Total households    Apartments        323399        503473        120          0        312333        515373        230        230        343213        519993        125        120 .
.
. .
.
. .
.
. .
.
.

Here, in the humanities and social information database 300, the total number of households and only the number of apartment households are stored for each predetermined area of the electronic cadastral map corresponding to the location information (X, Y), but the present invention is not limited thereto. The humanities and social information that can be stored may vary depending on the characteristics of the store, the products to be sold, the type of paid service, and the purpose of analyzing the commercial area.

The predicted business area information generating unit 400 receives (X, Y), which is a point value of a specific expected store that is planning to enter a store or currently enters a store, within a predetermined radius based on location information of a predicted store generated on an electronic map. Generating a plurality of cells having a predetermined size, generating humanities and social information for each cell through the population information of the population of the corresponding area in the humanities and social information database 300, and competing for the humanities and social information for each cell Calculate the expected revenue for the expected store by calculating the competition using the competition information, and by applying the humanities and competition information to the regression equation provided from the regression expression generation unit 100 to proceed with commercial prediction The estimated sales area for the expected store is calculated by calculating the commercial area on the electronic map through the commercial area prediction information to which the regression equation is applied.

Next, FIG. 2 is a diagram showing the detailed configuration of the regression generation unit shown in FIG. 1.

As shown in FIG. 2, the regression generation unit 100 includes a store location information designation unit 110, a cell generation unit 120, a cell information calculation unit 130, a store location information designation unit 140, Competitive information calculation unit 150, statistical analysis unit 160, regression derivation unit 170 is configured to include.

The store location information designation unit 110 receives the point coordinate values (X, Y) of a specific main store, which is a reference for generating a regression equation, and displays the location information of the store viewed on the electronic map by expressing it on the electronic map. do.

The cell generating unit 120 is a cell having a predetermined size (for example, 200 m) within a predetermined radius (for example, 20 km) centered on the location of the store on the electronic map designated by the store location information designating unit 110 ( Create a number of cells).

Here, a predetermined radius from the center of the store for generating the cells and the size of each cell may be differently applied according to various conditions that are different for each store.

The cell information calculating unit 130 displays the location information (X, Y) values of the customers of the customer information database 200 and the location information (X, Y) values of the humanities and social information database 300 on an electronic map. In the state indicated in, the customer information from the customer information database 200, that is, the customer sales, the number of customer visits, the total number of households, the number of apartment households of the humanities and social information database 300 is calculated for each cell and Create result table values accordingly.

As shown in FIG. 4, the cell information calculating unit 130 displays customer location information of the customer information database 200 and the humanities and social information database 300 as point data for each cell of the electronic map. Will be displayed.

In addition, as shown in FIG. 5, the cell information calculating unit 130 may include the customer sales of the customer information database 200, the number of visits to the customer, the total number of households and the number of apartment households of the humanities and social information database 300. By applying the information to each of the calculation, it is possible to generate a result table in which the sum of customer sales, the number of customer visits, the total number of households, and the number of apartment households are arranged for each identifier (ID) assigned to each cell.

The store location information designation unit 140 receives the point values (X, Y) of a specific competitive store in competition with the present store and displays the location information of the competitive store on the electronic map by expressing them on the electronic map. Specify.

The competition information calculation unit 150 stores the location information of the competition store from the store location information designation unit 140 and the accessibility information between the store and the competition store as competition information through the location information of the store. It calculates for each cell and applies the calculation result to the result table from the cell information operation unit 130 to generate a final result table. As a method for calculating the accessibility information, a straight line between the store and the competitive store. The distance measurement, the time at which the vehicle can move between the main store and the competitive store, and the time at which the walking can be moved between the main store and the competitive store are calculated for each cell.

As shown in FIG. 6A, the competition information calculating unit 150 expresses the distance from the competition store to each cell on the electronic map for each cell based on the present store, and as shown in FIG. 6B. As described above, the distance between the competition points with the shops for each cell is expressed for each cell on the electronic map based on the competition shops.

On the other hand, as a result of outputting the store distance information from the main store to the competitive store and the competitive point distance information from the competitive store as the result calculated by the competitive information calculating unit 150 from the cell information calculating unit 130 By applying the table value, as shown in FIG. 7, the distance to the store and the competition distance information are added to the result table in which the sum of customer sales, the number of customer visits, the total households, and the apartment households are arranged for each cell.

The statistical analysis unit 160 analyzes the statistical value of the result table information for each cell including the accessibility information with the competition store through the competition information calculation unit 150, the regression derivation unit 170 As a result of the statistical analysis from the statistical analysis unit 160, a regression formula for deriving the calculation of the sales forecast and the predicted commercial area is derived.

Here, the regression equation is a formula representing a predetermined function relationship between variables, and is composed of a variable value, an intercept value, and a coefficient value, and is used for estimation, test, and prediction using the regression equation between the variables.

The regression equation derived from the regression derivation unit 170 is as shown in Equation 1 below.

Where Y is the dependent variable (customer sales, the number of customer visits), Xi is the independent variable (total households, apartment households, distance to stores, distance to competitors, etc.), β0 is the intercept (constant term), and βi is Is the coefficient of each independent variable, and ε is an arbitrary term.

Next, FIG. 3 is a diagram showing the detailed configuration of the predictive business information information generating unit shown in FIG.

As illustrated in FIG. 3, the predicted business area information generating unit 400 includes a store location information specifying unit 410, a cell generating unit 420, a cell information calculating unit 430, and a store location information specifying unit 440. , Competitive information calculation unit 450, commercial area prediction unit 460, expected sales calculation unit 470, expected sales output unit 480, commercial area calculation unit 490, expected sales area calculation unit 500, expected sales The area output unit 510 is included.

The store location information designation unit 410 inputs a point value (X, Y) of an expected store for predicting the sales of the store although the store is expected to enter the store in which the sales forecast is required or the store that is currently in the store. The location information of the expected store is designated on the electronic map by receiving and expressing on the electronic map.

The cell generator 420 may select a cell having a predetermined size (for example, 200 m) within a predetermined radius (for example, 20 km) based on the location of the expected store on the electronic map designated by the store location information designation unit 410. Create a number.

FIG. 8 shows that the cell generator 420 generates a plurality of cells having a predetermined size within a predetermined radius around the expected location of the store.

The cell information calculation unit 430 displays the total number (X, Y) of the humanities and social information database 300 on the electronic map, and the total number of households and the number of apartment households in the humanities and social information database 300. The information is calculated for each cell to generate a result table value accordingly.

The store location information designation unit 440 receives a point value (X, Y) of a specific competitive store that may have a competition relationship with the expected store and displays the point value (X, Y) on the electronic map to locate the competitive store on the electronic map. Specify information.

The competition information calculating unit 450 calculates, for each cell, accessibility information between an expected store and a competition store through location information of the competition store from the store location information specifying unit 440 and location information between the expected store and the expected store. The calculation result is then applied to the result table from the cell information operation unit 430 to generate a final result table.

Here, as shown in FIG. 9, the competition information calculator 450 calculates a distance between a store with the competition store based on the expected store, and a distance between the store store with the expected store store based on the competition store. Allows individual calculations for each cell.

The commercial area predictor 460 estimates the number of sales and the number of visits expected for each cell based on the final result table value for each cell using the regression equation provided from the regression expression generator 100.

Here, as shown in FIG. 10, the commercial prediction unit 460 applies the regression equation of Equation 1 for each cell and inputs a value of the final result table to the regression equation to obtain "β ₀ + β _1. × total number of households + β ₂ × number of apartments + β ₃ × distance to store + β ₄ × competitive distance + ε = estimated sales "to estimate the estimated sales for each cell, and using the regression equation We also estimate the number of customer visits.

The estimated sales calculator 470 calculates the result of the estimated sales estimated from the commercial area predictor 460 by using a regression equation and applies the result to each cell on the electronic map, and numerically results for each cell. Calculates a value, and the estimated sales output unit 480 may visually discriminate or numerically predict the expected sales result for each cell on the electronic map calculated from the estimated sales calculator 470 as shown in FIG. 11. Print or print out the results.

The business area calculation unit 490 calculates a business area for the expected store by applying the expected sales and customer visit count values calculated for each cell using a regression equation from the business area prediction unit 46.

Here, in the case where the commercial area calculation unit 490 calculates the commercial area using only the expected sales amount, the commercial area calculation unit 490 calculates the commercial area by the process shown in FIGS. 12A to 12J.

The commercial area calculation unit 490 designates a cell to which the expected store belongs among a plurality of cells (FIG. 12A), and the cell having the highest revenue in eight neighboring directions from a cell including the designated expected store (ie And cells in the 7th direction) (FIG. 12b), and perform a process of merging the cells in the direction with the highest turnover among all neighboring 8-direction cells of the combined cells (FIG. 12c), and FIGS. 12d to 12b. After performing a process such as 12i to combine cells in a direction with high sales, the estimated sales ratio of all the combined cells is a preset ratio (eg, 60%, 80) as shown in FIG. 12J. %, 90%), the area defined by the merged cells selected up to that point is defined as the upper right area.

The expected sales area calculating unit 500 calculates a commercial area according to the result calculated by the commercial area calculation unit 490 as an expected sales area, and the expected sales area output unit 510 is shown in FIG. 13. As described above, the screen is output so that the expected sales area divided by the preset expected sales ratio is visually represented on the electronic map.

Next, the operation of the present invention made as described above will be described in detail with reference to the flowcharts of FIGS. 14 and 15.

First, a process of generating a regression equation will be described in detail with reference to the flowchart of FIG. 14.

First, the store location information designation unit 110 inputs (X, Y) coordinate values, which are point values of a specific main store, on the electronic map to designate the location of the main store (step S10), and the cell generator 120 ) Generates a plurality of cells having a predetermined size (e.g. 200m) within a predetermined radius (e.g. 20Km) around the location of the present store (step S11).

In this state, the cell information operation unit 130 calculates the location information (X, Y) values of the customer information database 200 and the humanities and social information database 300 for the plurality of cells generated by the cell generation unit 120. In the state displayed on the electronic map, the space for each cell using the customer sales information of the customer information database 200, the number of customer visits, the total number of households of the humanities and social information database 300, and the number of apartment households By performing the calculation, a result table calculated for each cell is generated (step S12).

Then, the store location information designation unit 140 inputs a point (X, Y) value for a specific competitive store that is in competition with the store and specifies the position of the corresponding competitive store on the electronic map (step) S13), the competition information calculation unit 150 is based on the location information of the main store, the distance between the stores of each cell between the competition stores based on the location of the competition stores based on the location information of the competition stores, based on the competition stores The final point table is generated by calculating the contention point distance with the present store by including the distance information with the store point of each cell and the information point of the contention point distance in the result table generated by the cell information operation unit 130 (step S14).

The statistical analysis unit 160 analyzes the statistical information of the final result table from the competition information calculation unit 150 (step S15), and the regression derivation unit 170 determines the final result for each cell according to the statistical analysis result. The regression equation as shown in Equation 1 is derived by applying the customer sales information, customer visit count information, total household count information, apartment household count information, apartment distance information, and competitive point distance information in the table (step S16). ).

Next, referring to the flowchart of FIG. 15, a process of generating a store forecast sales and a predicted commercial area will be described in detail.

First, the store location information designation unit 410 anticipates or enters the store, but inputs (X, Y) coordinate values, which are point values of a specific expected store for sales forecast, on the electronic map to determine the location of the corresponding store. (Step S20), the cell generation unit 420 generates a plurality of cells having a predetermined size (for example 200m) within a predetermined radius (for example 10Km) centering on the position of the expected store (Step S21). ).

In this state, the cell information operation unit 430 displays the location information (X, Y) value of the humanities and social information database 300 on the electronic map for the plurality of cells generated by the cell generation unit 420. In step S22, a spatial operation calculated for each cell is generated by performing a spatial operation for each cell by using the total household information and apartment household information of the humanities and social information database 300 (step S22).

In addition, when the store location information designation unit 440 inputs a point (X, Y) value for a specific competitive store that may be in competition with the expected store, and the position of the corresponding competitive store is designated on the electronic map (step S23), the competition information calculation unit 450 is based on the location information of the expected store, the distance between the stores of each cell between the competition stores based on the expected stores based on the location information of the competition stores, and based on the competition stores The final point table is generated by calculating the distance point of competition with the expected store, including the distance information with the points of each cell and the distance point of the competition in the result table generated by the cell information calculating unit 430 (step S24).

Next, the commercial area prediction unit 460 applies the regression equation generated from the regression expression generation unit 100 to predict the expected revenue for each cell and the number of customer visits based on the information value of the final result table ( Step S25), the estimated sales calculation unit 470 calculates the expected sales based on the prediction result of the commercial area predictor 460 (step S26), and the screen can be visually viewed through the expected sales output unit 480. Output or print out (step S27).

Meanwhile, the commercial area calculation unit 490 performs an operation for generating the commercial area on the electronic map through the estimated revenue for each cell and the number of visits to the customer, which are calculated using the regression equation in the commercial area predictor 460. F. neighboring cells with the highest expected sales or customer visits are merged with each other based on the cell where the expected store is located, and the cells with the highest expected sales or customer visits are combined among neighboring cells around the merged cells. Repeats the process (step S28).

While performing the process of merging the cells repeatedly, it is determined whether the sales ratio of the combined cells reaches a predetermined expected sales ratio (for example, 60%, 80%, 90%) to complete generation of the trade zone. In step S29, when the generation of the commercial area is to be completed, the expected sales area calculation unit 500 calculates the commercial area calculated by the commercial area calculation unit 490 as the expected sales area (step S30). Through the expected sales area output unit 510, the screen output or the print output is made possible to be visually searched (step S31).

Meanwhile, in the present invention made as described above, when inputting an existing store as an expected store to predict sales for a store that is already entered, the actual sales area of the corresponding store as shown in FIG. 16A and FIG. As shown in 16b, the predicted sales area of the store may be different, and it is possible to improve the sales by identifying the gap between the sales area and the predicted sales area of each cell, but to improve the sales by discovering areas that do not carry out marketing. It is possible to make it possible.

While specific embodiments of the present invention have been described and illustrated above, it will be apparent that the present invention may be embodied in various modifications by those skilled in the art. Such modified embodiments should not be understood individually from the technical spirit or the prospect of the present invention, but should fall within the claims appended to the present invention.

1 is a view showing the overall configuration for the sales forecasting and predictive commercial area generation system using the cell statistics technique according to the present invention,

2 is a view showing a detailed configuration of the regression generation unit shown in FIG.

3 is a diagram illustrating a detailed configuration of a predicted business area information generating unit illustrated in FIG. 1;

4 is a diagram illustrating a process of calculating a population DB and a customer DB for each cell according to the present invention;

5 is a view showing a result table value calculated for each cell according to the present invention;

6A and 6B are diagrams showing distances from stores of each cell and distances from competition points according to the present invention;

7 is a view showing a final result table calculated for each cell according to the present invention;

8 is a diagram illustrating a cell generation screen after inputting a predicted store to an arbitrary area according to the present invention;

9 is a diagram illustrating a cell screen on which operation information is input according to the present invention;

10 is a view showing a state in which the expected revenue for each cell is calculated according to the present invention;

11 is a diagram showing a calculation result of the expected revenue per cell according to the present invention;

12A to 12J are views illustrating a process of forming a trade zone by designating a cell to which a store belongs according to the present invention, respectively;

FIG. 13 is a diagram illustrating a state in which a predictive trade zone is generated on a map based on an expected sales amount according to the present invention;

14 is a flowchart illustrating a process of generating a regression equation according to a method of generating revenue forecasting and predictive commercial volume using a cell statistics method according to the present invention;

15 is a flowchart illustrating a process of generating a store forecast sales and a forecast commercial area according to the method of generating sales forecast and the predicted commercial volume using the cell statistics method according to the present invention;

16A and 16B are diagrams exemplarily illustrating a state in which actual sales and forecast sales are respectively shown on a map according to the present invention.

<Explanation of symbols for the main parts of the drawings>

100: regression generation unit, 110, 140, 410, 440: store location information designation unit,

120,420: cell generator, 130,430: cell information calculator,

150,450: competitive information calculation unit, 160: statistical analysis unit,

170: regression derivation unit, 460: commercial business unit,

470: expected sales calculation unit, 480: expected sales output unit,

490: business area calculation unit, 500: expected sales area calculation unit,

510: expected sales area output.

Claims (13)

delete A first step of generating a plurality of cells having a predetermined size around a location of a specific expected store in a cell generation unit; A second step of generating, by a cell information calculation unit, a result table including humanities and social information for each cell by applying humanities and social information of a corresponding region to each cell around the expected store; A third step of receiving a point value of a competitive store from a store location information designating unit and designating a location of a competitive store in competition with the expected store; The competitive information calculation unit calculates a store distance for each cell of the competitive store based on the expected store based on the position of the competitive store and the expected store, and compares the competitive store for each cell with the expected store based on the competitive store. Calculating a distance; A fifth step of including, by the competition information calculation unit, a store distance for each cell and a competition point distance in the result table; A commercial prediction unit calculates the estimated sales and the number of visits by each cell by calculating the humanities and social information of the result table, the store distance, and the competition distance by applying a variable to a regression equation (로 式). Step 6; And The commercial area calculation unit repeatedly performs the process of merging the cells with the highest sales among the eight directions neighboring the cells including the expected stores by using the estimated sales predicted for each cell and the number of customer visits. And a seventh step of generating an expected sales area based on the merged cells when the expected sales ratio reaches a preset ratio. The method of claim 2, In the sixth step, the regression equation,

Where Y is the dependent variable (customer sales, the number of customer visits), Xi is the independent variable (total households, apartment households, distance to stores, distance to competitors, etc.), β0 is the intercept (constant term), βi Is the coefficient of each independent variable, and ε is an arbitrary term) Revenue forecasting and forecasting business zone generation method using a cell statistical method characterized in that consisting of. The method of claim 2, Before the first step, generating a plurality of cells having a predetermined size around the location of the particular main store that is the basis of the regression generation; Generating a result table including customer information and humanities and social information for each cell by applying the customer information of the store and humanities and social information of the region to each cell around the store; Based on the location of the competitive store that is in competition with the main store and the location of the main store, the store distance of each cell with the competitive store is calculated based on the main store, and each of the stores with the main store is calculated based on the competitive store. Calculating a competition point distance for each cell to include in the result table; Deriving the regression equation by analyzing the statistical value of the customer information, humanities and social information, the store distance, the competitive distance in the result table by the variable further comprises the step of calculating the sales forecast and predictive business How to produce. The method of claim 4, wherein The customer information is a sales forecasting method using the cell statistics method characterized in that any one of the sales information divided by the address and location coordinate value of each customer, the customer visit information. The method of claim 2, The humanities and social information information is one of the total number of household information divided by the position coordinate value, and the number of apartment household information, sales forecasting and predictive commercial area generation method using a cell statistics method. delete delete A cell generator for generating a plurality of cells having a predetermined size around a specific expected store location; A cell information calculator configured to generate a result table including the humanities and social information for each cell by applying the humanities and social information of the region to each cell around the expected store generated by the cell generator; A store location information designation unit for designating a location of a competition store in competition with the expected store; Calculating a store distance for each cell with a competitive store based on a predicted store based on the position of the competitive store and the position of the expected store, and calculating a competitive point distance for each cell with an expected store based on the competitive store, A competition information calculation unit including a store distance and a competition point distance for each cell in the result table; A commercial area predictor for predicting the expected sales and the number of visits of each cell by calculating and applying the humanities and social information of the result table, the store distance, and the competition distance as variables to a regression equation; And The process of merging the cells with the highest sales among the eight directions neighboring the cells including the expected stores by using the estimated sales predicted for each cell by the commercial area predictor and the number of customer visits repeatedly By performing, the sales forecasting and forecasting commercial volume generation system using a cell statistics technique, characterized in that it comprises a commercial area calculation unit for generating an expected sales region based on the cells merged when the expected sales ratio reaches a preset ratio; . The method of claim 9, The regression formula,

Where Y is the dependent variable (customer sales, the number of customer visits), Xi is the independent variable (total households, apartment households, distance to stores, distance to competitors, etc.), β0 is the intercept (constant term), βi Is the coefficient of each independent variable, and ε is an arbitrary term) Revenue forecasting and forecast commercial area generation system using a cell statistics method, characterized in that consisting of. The method of claim 9, A cell generation unit generating a plurality of cells having a predetermined size around a location of a specific main store, which is a reference of the regression generation; A cell information operation unit which generates a result table including customer information and humanities and social information for each cell by applying the customer information of the store and the humanities and social information of the region for each cell around the store; Based on the location of the competitive store that is in competition with the main store and the location of the main store, the store distance of each cell with the competitive store is calculated based on the main store, and each of the stores with the main store is calculated based on the competitive store. Competitive information calculation unit for calculating the competition point distance for each cell included in the result table, And a regression derivation unit configured to derive the regression equation by analyzing statistical values as variables of customer information, humanities and social information, store distance, and competition point distance in the result table. Predictive business rights generation system. The method of claim 11, The customer information is a sales forecasting and prediction business ticket generation system using a cell statistics method, characterized in that any one of the customer information and the number of sales information divided by the address and location coordinate value of each customer. The method of claim 9, The humanities and social information is a sales prediction and prediction commercial area generation system using a cell statistical method, characterized in that any one of the total number of household information divided by the position coordinate value, and the number of apartment households.

Images