System and method for customer behavior movement frequency prediction in a store

• US 7,778,863 B2
• Filed: 09/13/2005
• Issued: 08/17/2010
• Est. Priority Date: 02/09/2005
• Status: Expired due to Fees

• Current Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation)
• Original Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation)
• Inventors: Yoshida, Takufumi, Koiso, Takashi
• Primary Examiner(s): Jarrett; Scott L
• Application Number:
  US11/224,036
• Publication Number:
  US 20060179014A1
• Time in Patent Office: 1,799 Days
• Field of Search: 705/10
• US Class Current: 705/7.31
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0202 Market predictions or forecasting for commercial activities
• CPC Class Codes: G06Q 30/0204 Market segmentation

Abstract

According to an aspect of the present invention, there is provided with a behavior prediction apparatus including: an area attribute database which stores area attributes of each of a plurality of areas in an activity area of customers; an inter-area attribute database which stores inter-area attributes between two areas; a behavior history database which stores behavior history of the customers in the activity area; a movement frequency database generator which generates a movement frequency database representing a movement frequency between the two areas on the basis of the individual behavior history database; and a movement frequency model estimator which estimates a value of a parameter in a movement frequency model having area attributes and inter-area attributes as its input and a movement frequency as its output.

Claims

1. A customer behavior prediction apparatus comprising:

an area attribute database which stores area attributes of each of a plurality of areas in an activity area of customers in a store;

an inter-area attribute database which stores inter-area attributes between the areas in the activity area;

a behavior history database which stores behavior history of the customers in the activity area;

a movement frequency database generator which generates a movement frequency database representing a movement frequency between each of the areas in the activity area on the basis of the behavior history database;

a movement frequency model estimator which estimates a value of a parameter in a movement frequency model having the area attributes and the inter-area attributes of the areas in the activity area as inputs and a movement frequency, as a probability distribution, between each of the areas in the activity area as an output;

a movement frequency prediction unit which generates a prediction movement frequency database which represents the movement frequency between the areas of each of the customers in the activity area corresponding to a maximum probability or an average movement frequency between the areas in the activity area based on the probability distribution out of the movement frequency model;

an individual attribute database which stores the individual attributes of each of the customers;

a behavior selection model estimator which estimates a value of a parameter in a behavior selection model to obtain behavior selection of a customers at a subject time from the individual attributes of the customer, the area attributes and the inter-area attributes of the areas in the activity area, a movement frequency between each of the areas in the activity area, and behavior history of the customers ending at the subject time; and

a behavior selection prediction unit which inputs individual attributes of a subject customer, area attributes and inter-area attributes of areas in a subject activity area, a movement frequency between each of the areas in the subject activity area estimated by the movement frequency model, and behavior history of the subject customer ending at the subject time in the subject activity area to the behavior selection model, and predicts behavior selection of the subject customer at the subject time.

2. The customer behavior prediction apparatus according to claim 1, wherein the behavior selection model uses area attributes of an area where the subject customer individual as the subject of the prediction is located and inter-area attributes including the area where the subject customer is located this area, as the area attributes and the inter-area attributes in the activity area as the subject of the prediction, and uses a movement frequency of inter-area having at least this area as a shift origin or a shift destination, as the movement frequency in the subject activity area as the subject of the prediction.

3. The customer behavior prediction apparatus according to claim 1, wherein the behavior selection model is a model that outputs probabilities with which respective behavior selections corresponding to the behavior selection model are selected by the customer individual, and

the behavior selection prediction unit predicts behavior selection of the subject customer individual from the probabilities output by the behavior selection model.

4. The customer behavior prediction apparatus according to claim 1, wherein the behavior selection prediction unit predicts transition of behavior selection of the subject customer individual as the subject of the prediction by using a simulation model, and successively records the behavior selection of the subject customer individual as behavior history.

5. The customer behavior prediction apparatus according to claim 4, further comprising a moving trail data generator which generates moving trail data indicating movement history of the individual as the subject customer of the prediction, from the behavior history.

6. The customer behavior prediction apparatus according to claim 5, further comprising a moving trail analysis unit which conducts a moving trail analysis by using the moving trail data of a plurality of customers.

7. A customer behavior prediction method comprising:

reading out data from a behavior history database which stores behavior history of customers in a plurality of areas in an activity area in a store;

generating a movement frequency database representing a movement frequency between the areas in the activity area;

reading out data from an area attribute database which stores area attributes of each of the a plurality of areas in the activity area, an inter-area attribute database which stores inter-area attributes between each of the areas in the activity area, and the movement frequency database;

estimating, using a computer, a value of a parameter in a movement frequency model having the area attributes and the inter-area attributes of the areas in the activity area as inputs, and a movement frequency, as a probability distribution, between each area in the activity area as an output;

generating, using a computer, a prediction movement frequency database which represents the movement frequency between the areas of each of the customers in the activity area corresponding to a maximum probability or an average movement frequency between the areas in the activity area based on the probability distribution out of the movement frequency model;

reading out data from an individual attribute database which stores the individual attributes of each of the customers;

estimating, using a computer, a value of a parameter in a behavior selection model to obtain behavior selection of a customer at a subject time from the individual attributes of the customer, the area attributes and the inter-area attributes of the areas in the activity area, a movement frequency between each area in the activity area, and behavior history of the customer ending at the subject time; and

inputting individual attributes of a subject customer, area attributes and inter-area attributes in a subject activity area, a movement frequency between each area in the subject activity area estimated by the movement frequency model, and behavior history of the subject customer ending at the subject time in the subject activity area to the behavior selection model, the behavior selection model predicting behavior selection of the subject customer at the subject time.

8. A computer-readable recording medium storing computer-executable instructions for causing customer behavior prediction program to make a computer to execute a behavior prediction method, the behavior prediction method comprising:

reading out data from a behavior history database which stores behavior history of customers in a plurality of areas in an activity area in a store;

generating a movement frequency database representing a movement frequency between the areas in the activity area;

reading out data from an area attribute database which stores area attributes of each of the a plurality of areas in the activity area, an inter-area attribute database which stores inter-area attributes between each of the areas in the activity area, and the movement frequency database;

estimating a value of a parameter in a movement frequency model having the area attributes and the inter-area attributes of the areas in the activity area as inputs, and a movement frequency, as a probability distribution, between each area in the activity area as an output;

generating a prediction movement frequency database which represents the movement frequency between the areas of each of the customers in the activity area corresponding to a maximum probability or an average movement frequency between the areas in the activity area based on the probability distribution out of the movement frequency model;

reading out data from an individual attribute database which stores the individual attributes of each of the customers;

estimating a value of a parameter in a behavior selection model to obtain behavior selection of a customer at a subject time from the individual attributes of the customer, the area attributes and the inter-area attributes of the areas in the activity area, a movement frequency between each area in the activity area, and behavior history of the customer ending at the subject time; and

inputting individual attributes of a subject customer, area attributes and inter-area attributes in a subject activity area, a movement frequency between each area in the subject activity area estimated by the movement frequency model, and behavior history of the subject customer ending at the subject time in the subject activity area to the behavior selection model, the behavior selection model predicting behavior selection of the subject customer at the subject time.