JP2013029883A5

JP2013029883A5 -

Info

Publication number: JP2013029883A5
Application number: JP2011163492A
Authority: JP
Filing date: 2011-07-26
Publication date: 2014-04-17
Anticipated expiration: 2031-07-26

Description

上記従来例の問題点を解決するための本発明は、店舗特性を分析するプロファイリングシステムであって、コンピュータの記憶部に複数の店舗に関するデータと統計データを記憶し、制御部がプログラムを動作させて実行する処理手段として、特定エリア内の複数の店舗について複数の店舗に関するデータと統計データを変数として変数間相関表を作成し、変数を確定する変数決定処理手段と、確定された変数について主成分分析処理を行い、主成分から因子を特定し、因子の主成分得点を算出し、変数と主成分得点との相関を演算し、相関係数を主成分負荷量とする主成分負荷量行列を生成する主成分分析処理手段と、因子でクラスター分析を行い、クラスター別の因子毎に平均値を演算して、クラスター別の因子毎に平均表を生成するクラスター分析処理手段と、平均表を基に、特定エリアにおける店舗特性のレポートを生成するレポート生成処理手段とを有することを特徴とする。 The present invention for solving the problems of the above conventional example is a profiling system for analyzing store characteristics, storing data and statistical data about a plurality of stores in a storage unit of a computer, and causing the control unit to operate the program. executing Te as a processing means, to create a correlation table between variables and statistics data for a plurality of shops and variables for a plurality of stores within a particular area, a variable determination processing means for determining the variables, the determined variable Principal component analysis is performed on, the factor is identified from the principal component, the principal component score of the factor is calculated, the correlation between the variable and the principal component score is calculated, and the correlation coefficient is the principal component load a principal component analysis processing means for generating an amount matrix performs cluster analysis in factor, for each cluster-specific factors by calculating the average value, to generate a flat Hitoshihyo for each cluster-specific factors click And star analysis processing means, based on a flat Hitoshihyo, and having a report generating means for generating a report store properties in a particular area.

本発明は、店舗特性を分析するプロファイリングシステムであって、コンピュータの記憶部に複数の店舗に関するデータと統計データを記憶し、制御部がプログラムを動作させて実行する処理手段として、特定エリア内の複数の店舗について複数の店舗に関するデータと統計データを変数として変数間相関表を作成し、変数を確定する変数決定処理手段と、確定された変数について主成分分析処理を行い、主成分から因子を特定し、因子の主成分得点を算出し、変数と主成分得点との相関を演算し、相関係数を主成分負荷量とする主成分負荷量行列を生成する主成分分析処理手段と、因子でクラスター分析を行い、因子を用いて小分類のクラスター間の距離を計算して小分類のクラスター分析の表を生成し、前記小分類のクラスター別の因子毎に平均値を演算して、当該平均値を用いて中分類のクラスター間の距離を計算して、当該計算された距離の値に応じてクラスターをグループ化して分類し、計算された距離に基づいてグループの結合を行ってクラスター組み替えの適正化を行って、中分類のクラスター別の平均表を生成するクラスター分析処理手段と、平均表を基に、特定エリアにおける店舗特性のレポートを生成するレポート生成処理手段とを有することを特徴とする。
本発明は、本発明は、上記プロファイリングシステムにおいて、レポート生成処理手段が、クラスター分析処理手段で生成された平均表を基に、拠点が含まれる特定エリアについて、１つ又は２つの変数に対するクラスター毎の出現率を表示する地域特性のレポートを生成することを特徴とする。 The present invention is a profiling system for analyzing store characteristics, storing data and statistical data relating to a plurality of stores in a storage unit of a computer, and a processing unit that operates and executes a program as a processing unit in a specific area. Create a correlation table between variables using multiple store data and statistical data as variables for multiple stores, variable decision processing means to confirm the variables, and principal component analysis processing for the confirmed variables, Principal component analysis processing means for generating a principal component load matrix that identifies and calculates a principal component score of a factor, calculates a correlation between a variable and a principal component score, and uses a correlation coefficient as a principal component load amount; Perform cluster analysis in, calculate the distance between subclass clusters using factors, and generate a subclass cluster analysis table. The average value is calculated, the distance between the middle class clusters is calculated using the average value, the clusters are grouped and classified according to the calculated distance value, and based on the calculated distance. A cluster analysis processing means that generates an average table for each of the middle-class clusters by combining groups and optimizing the cluster rearrangement, and a report that generates a report of store characteristics in a specific area based on the average table Generation processing means.
The present invention is the above profiling system, in which the report generation processing unit is based on the average table generated by the cluster analysis processing unit for each cluster for one or two variables in a specific area including a base. The report of the regional characteristic which displays the appearance rate of is characterized by generating.

本発明によれば、コンピュータの記憶部に複数の店舗に関するデータと統計データを記憶し、制御部がプログラムを動作させて実行する処理手段として、変数決定処理手段が、特定エリア内の複数の店舗について複数の店舗に関するデータと統計データを変数として変数間相関表を作成し、変数を確定し、主成分分析処理手段が、確定された変数について主成分分析処理を行い、主成分から因子を特定し、因子の主成分得点を算出し、変数と主成分得点との相関を演算し、相関係数を主成分負荷量とする主成分負荷量行列を生成し、クラスター分析処理手段が、因子でクラスター分析を行い、クラスター別の因子毎に平均値を演算して、クラスター別の因子毎に平均表を生成し、レポート生成処理手段が、平均表を基に、特定エリアにおける店舗特性のレポートを生成するプロファイリングシステムとしているので、店舗特性についてプロファイリングデータを利用して得点化し、店舗特性をレポートできる効果がある。
また、本発明によれば、コンピュータの記憶部に複数の店舗に関するデータと統計データを記憶し、制御部がプログラムを動作させて実行する処理手段として、変数決定処理手段が、特定エリア内の複数の店舗について複数の店舗に関するデータと統計データを変数として変数間相関表を作成し、変数を確定し、主成分分析処理手段が、確定された変数について主成分分析処理を行い、主成分から因子を特定し、因子の主成分得点を算出し、変数と主成分得点との相関を演算し、相関係数を主成分負荷量とする主成分負荷量行列を生成し、クラスター分析処理手段が、因子でクラスター分析を行い、因子を用いて小分類のクラスター間の距離を計算して小分類のクラスター分析の表を生成し、前記小分類のクラスター別の因子毎に平均値を演算して、当該平均値を用いて中分類のクラスター間の距離を計算して、当該計算された距離の値に応じてクラスターをグループ化して分類し、計算された距離に基づいてグループの結合を行ってクラスター組み替えの適正化を行って、中分類のクラスター別の平均表を生成し、レポート生成処理手段が、平均表を基に、特定エリアにおける店舗特性のレポートを生成するプロファイリングシステムとしているので、店舗特性についてプロファイリングデータを利用して得点化し、店舗特性をレポートできる効果がある。
According to the present invention, as a processing means for storing data and statistical data relating to a plurality of stores in the storage unit of the computer and causing the control unit to operate and execute the program, the variable determination processing unit includes the plurality of stores in the specific area. for creating a correlation table between variables and data and statistical data for a plurality of stores as a variable, to confirm the variables, the principal component analysis processing unit performs a principal component analysis process for defined variables, factors from the main component , Calculate the principal component score of the factor, calculate the correlation between the variable and the principal component score, generate a principal component load matrix with the correlation coefficient as the principal component load, and the cluster analysis processing means, perform cluster analysis in factor, for each cluster-specific factors by calculating the average value, to generate a flat Hitoshihyo for each cluster-specific factors, the report generating means, based on flat Hitoshihyo, in a specific area Since the profiling system for generating 舗特 of reports, and scored using the profiling data for the store characteristics, the effect of the store characteristics can report.
Further, according to the present invention, the variable determination processing means includes a plurality of variables in the specific area as processing means for storing data and statistical data relating to a plurality of stores in the storage unit of the computer and causing the control unit to operate and execute the program. Create a correlation table between variables using multiple store data and statistical data as variables, determine the variables, and the principal component analysis processing means performs principal component analysis on the determined variables, and the factors from the principal components , Calculate the principal component score of the factor, calculate the correlation between the variable and the principal component score, generate a principal component load matrix with the correlation coefficient as the principal component load, and the cluster analysis processing means, Perform cluster analysis by factor, calculate the distance between subclass clusters using the factor, generate a subclass cluster analysis table, and calculate the average value for each factor of each subclass cluster. Then, the distance between the middle class clusters is calculated using the average value, the clusters are grouped and classified according to the calculated distance value, and the group combination is performed based on the calculated distance. Since the reclassification of the cluster is performed to generate an average table for each cluster in the middle class, the report generation processing means is a profiling system that generates a report of store characteristics in a specific area based on the average table. The store characteristics can be scored using profiling data, and the store characteristics can be reported.

Claims

A profiling system for analyzing store characteristics,
As processing means for storing data and statistical data on a plurality of stores in a storage unit of a computer, and causing the control unit to operate and execute a program
A variable determination processing means for data and statistical data for a plurality of stores to create a correlation table between variables as a variable, to determine the variable for the plurality of stores within a specific area,
A principal component analysis process is performed on the determined variable, a factor is identified from the principal component, a principal component score of the factor is calculated, a correlation between the variable and the principal component score is calculated, and a correlation coefficient is calculated. Principal component analysis processing means for generating a principal component load matrix as component loads,
Perform cluster analysis in the factor, for each cluster-specific factors by calculating the average value, the cluster analysis processing means for generating a flat Hitoshihyo for each cluster-specific factors,
The flat Hitoshihyo based on profiling system; and a report generating means for generating a report store characteristics in the specific area.

A profiling system for analyzing store characteristics,
As processing means for storing data and statistical data on a plurality of stores in a storage unit of a computer, and causing the control unit to operate and execute a program,
A variable determination processing means for creating a correlation table between variables for a plurality of stores in a specific area using the data and statistical data on the plurality of stores as variables, and determining the variables;
A principal component analysis process is performed on the determined variable, a factor is identified from the principal component, a principal component score of the factor is calculated, a correlation between the variable and the principal component score is calculated, and a correlation coefficient is calculated. Principal component analysis processing means for generating a principal component load matrix as component loads,
Perform cluster analysis with the factor, calculate the distance between the subclass clusters using the factor, generate a subclass cluster analysis table, and calculate the average value for each factor of the subclass cluster Then, the distance between the middle class clusters is calculated using the average value, the clusters are grouped and classified according to the calculated distance value, and the combination of the groups is determined based on the calculated distance. A cluster analysis processing means for performing cluster optimization and generating an average table for each middle class cluster;
A profiling system comprising report generation processing means for generating a report of store characteristics in the specific area based on the average table.

Claims a report generating means, based on the flat Hitoshihyo generated by cluster analysis processing unit, a store characteristics and generating a report of the store properties to be displayed by a factor name and mean values for each cluster The profiling system according to 1 or 2 .

Report generating means, based on the flat Hitoshihyo generated by cluster analysis processing means, for a particular area, the displayed shop characteristics reports that a plurality of stores in the specified area is color-coded for each cluster on the map claim 1 or 2 profiling system wherein generating a.

The profiling system according to any one of claims 1 to 4 , wherein the principal component analysis processing means identifies a factor from the principal component based on an eigenvalue and a cumulative contribution rate in the principal component analysis.

The profiling system according to any one of claims 1 to 5 , wherein the cluster analysis processing means performs cluster analysis using variables in addition to factors.

Cluster analysis processing means, profiling system of claim 1, wherein generating a report store characteristics for displaying the average value of a plurality of variables for each cluster.

Profiling system according to claim 1 or 2, wherein the report generating means generates a portfolio color display store for each cluster using a plurality of variables.

Claim 1 or 2 profiling system wherein the report generating means generates a scatter plot for color display store for each cluster using a plurality of principal components.

A spider chart in which the report generation processing unit calculates an average value for each factor from the result of the principal component analysis, calculates a difference between the average value and the extracted factor value of the store, and arranges the plurality of factor names profiling system according to claim 1 or 2, wherein the generating an analysis graph drawing a difference between the retailer.

)
When the report generation processing means generates a discriminant model using canonical discriminant analysis from the results of principal component analysis and cluster analysis, and the new store data is input and set using the discriminant model, the new store The profiling system according to claim 1 or 2, wherein a quick report for calculating and displaying a probability corresponding to a cluster is generated.

A computer program used in a profiling system for analyzing store characteristics,
Computer
A variable determination processing means for creating a correlation table between variables for a plurality of stores in a specific area using the data and statistical data on the plurality of stores as variables, and determining the variables;
A principal component analysis process is performed on the determined variable, a factor is identified from the principal component, a principal component score of the factor is calculated, a correlation between the variable and the principal component score is calculated, and a correlation coefficient is calculated. Principal component analysis processing means for generating a principal component load matrix as component loads,
Cluster analysis processing means for performing cluster analysis with the factors, calculating an average value for each factor for each cluster, and generating an average table for each factor for each cluster;
A program that functions as a report generation processing unit that generates a report of store characteristics in the specific area based on the average table.

A computer program used in a profiling system for analyzing store characteristics,
Computer
A variable determination processing means for creating a correlation table between variables for a plurality of stores in a specific area using the data and statistical data on the plurality of stores as variables, and determining the variables;
A principal component analysis process is performed on the determined variable, a factor is identified from the principal component, a principal component score of the factor is calculated, a correlation between the variable and the principal component score is calculated, and a correlation coefficient is calculated. Principal component analysis processing means for generating a principal component load matrix as component loads,
Perform cluster analysis with the factor, calculate the distance between the subclass clusters using the factor, generate a subclass cluster analysis table, and calculate the average value for each factor of the subclass cluster Then, the distance between the middle class clusters is calculated using the average value, the clusters are grouped and classified according to the calculated distance value, and the combination of the groups is determined based on the calculated distance. A cluster analysis processing means for performing cluster optimization and generating an average table for each middle class cluster;
A program that functions as a report generation processing unit that generates a report of store characteristics in the specific area based on the average table.