Method and apparatus for end-to-end retail store site optimization

• US 8,239,245 B2
• Filed: 01/22/2008
• Issued: 08/07/2012
• Est. Priority Date: 01/22/2008
• Status: Expired due to Fees

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Bai, Xin Xin, Dong, Jin, Li, Ta-Hsin, Yin, Wen Jun, Zhang, Bin, Zhang, Cindy Q.
• Primary Examiner(s): Rines, R. David
• Assistant Examiner(s): SCHEUNEMANN, RICHARD N
• Application Number:
  US12/017,673
• Publication Number:
  US 20090187464A1
• Time in Patent Office: 1,659 Days
• Field of Search: 705/10
• US Class Current: 705/7.37
• CPC Class Codes: G06Q 10/04 Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem" market predictions or forecasting for commercial activities G06Q30/0202
• CPC Class Codes: G06Q 30/0205 Location or geographical consideration

Abstract

A method and apparatus for end-to-end retail store one-stop site configuration integrates multiple data sources, identifying key customers, forecasting merchandise demand. Site configuration is formulated as a mathematical optimization problem with both in-store and external data as input to the problem whose solution provides proper suggestions for retail store transformation.

Claims

1. A method of providing store site configuration, comprising:

integrating in-store and external data from multiple sources into a geographic information system platform;

determining customer segment profile, customer geo-distribution and customer demand from the integrated data in the geographic information system platform;

modeling and forecasting potential customer geo-distribution using said customer segment profile, said customer geo-distribution and said customer demand;

modeling and forecasting potential merchandise demand using said potential customer geo-distribution;

deriving one or more gaps using said forecasted potential customer geo-distribution or forecasted potential merchandise demand or combination of both; and

determining, by a processor, site configuration for a network of stores based on said one or more gaps, said site configuration providing recommendations for location, format, capacity, merchandise mix and customer segment by solving an optimization model that simultaneously determines said location, format, capacity, merchandise mix and customer segment,

the optimization model including

2. The method of claim 1, wherein said one or more gaps include:

gap between the number of potential customers and actual customers.

3. The method of claim 1, wherein said one or more gaps include:

gap between potential demand and actual sales of merchandise.

4. The method of claim 1, wherein said one or more gaps include:

gap between potential demand of merchandise by customer segment and actual demand of merchandise by customer segment.

5. The method of claim 1, wherein said in-store and external data from multiple sources include:

store information, transaction record, merchandise data, membership record, market survey data, competitor information, geographic data, or demographic data, or combinations thereof.

6. The method of claim 1, wherein the step of determining customer segment profile, customer geo-distribution and customer demand includes using a clustering algorithm to determine customer segment profile, customer geo-distribution and customer demand.

7. The method of claim 1, wherein the step of modeling and forecasting potential customer geo-distribution includes using statistical data mining algorithm to model and forecast potential customer geo-distribution.

8. The method of claim 1, wherein the step of determining site configuration includes building an optimization model to configure one or more stores based on said one or more gaps.

9. The method of claim 8, wherein the optimization model maximizes total profit of said one or more stores in a store network, the optimization model based on location, format, capacity, merchandise mix and customer segment factors.

10. The method of claim 1, further including:

presenting the determined site configuration using a geographical map.

11. The method of claim 1, wherein the step of integrating further includes:

converting said data into geographic information system format.

12. The method of claim 1, wherein said integrated data is represented with spatial attributes and non-spatial attributes.

13. A system for providing store site configuration, comprising:

a processor;

data integration module operable to integrate in-store and external data from multiple sources into a geographic information system platform;

customer analytics module operable to determine customer segment profile, customer geo-distribution and customer demand from the integrated data in the geographic information system platform, the customer analytics module further operable to model and forecast potential customer geo-distribution using said customer segment profile, said customer geo-distribution and said customer demand, and to model and forecast potential merchandise demand using said potential customer geo-distribution;

gap analysis module operable to derive one or more gaps using said forecasted potential customer geo-distribution or forecasted potential merchandise demand or combination of both; and

configuration decision module operable execute on the processor and to determine site configuration for a network of stores based on said one or more gaps, said site configuration providing recommendations for location, format, capacity, merchandise mix and customer segment by solving an optimization model that simultaneously determines said location, format, capacity, merchandise mix and customer segment

the optimization model including

14. The system of claim 13, wherein said one or more gaps include:

gap between the number of potential customers and actual customers;

gap between potential demand and actual sales of merchandise;

gap between potential demand of merchandise by customer segment and actual demand of merchandise by customer segment;

or

combinations thereof.

15. The system of claim 13, wherein said in-store and external data from multiple sources include:

store information, transaction record, merchandise data, membership record, market survey data, competitor information, geographic data, or demographic data, or combinations thereof.

16. The system of claim 13, wherein the configuration decision module includes an optimization model operable to configure one or more stores based on said one or more gaps, the optimization model further operable to maximizes total profit of said one or more stores in a store network, the optimization model based on location, format, capacity, merchandise mix and customer segment factors.

17. The system of claim 13, further including:

a graphical user interface operable to present the determined site configuration using a geographical map.

18. A program storage device readable by a machine, tangibly embodying a program of instructions executable by the machine to perform a method of providing store site configuration, comprising:

integrating in-store and external data from multiple sources into a geographic information system platform;

determining customer segment profile, customer geo-distribution and customer demand from the integrated data in the geographic information system platform;

modeling and forecasting potential customer geo-distribution using said customer segment profile, said customer geo-distribution and said customer demand;

modeling and forecasting potential merchandise demand using said potential customer geo-distribution;

deriving one or more gaps using said forecasted potential customer geo-distribution or forecasted potential merchandise demand or combination of both; and

determining site configuration for a network of stores based on said one or more gaps, said site configuration providing recommendations for location, format, capacity, merchandise mix and customer segment by solving an optimization model that simultaneously determines said location, format, capacity, merchandise mix and customer segment,

the optimization model including

19. The program storage device of claim 18, wherein said one or more gaps include:

gap between the number of potential customers and actual customers;

gap between potential demand and actual sales of merchandise;

gap between potential demand of merchandise by customer segment and actual demand of merchandise by customer segment;

or

combinations thereof.