Causal performance analysis approach for store merchandizing analysis

Patent metadata

Field	Value
Publication number	US-10956850-B2
Application number	US-201615334367-A
Country	US
Kind code	B2
Filing date	Oct 26, 2016
Priority date	May 16, 2016
Publication date	Mar 23, 2021
Grant date	Mar 23, 2021

Abstract

Causal performance analysis for store merchandising may be provided. A clustering technique may be performed based on target store location data and existing store data. Based on the clustering technique, a peer selection group is determined comprising a group of stores determined to have similar attributes to the target store location. Sales distortions for a plurality of divisions associated with the group of stores in the peer selection group may be determined. A distortion matrix may be generated comprising a ranked list of the plurality of divisions. A merchandise mix recommendation for the target store location may be presented via a user interface device.

First claim

We claim:

1. A computer-implemented method of providing causal performance analysis for store merchandising, the method performed by one or more hardware processors, the method comprising:
receiving via a communication network target store location data associated with a target store location, the target store location data including at least information associated with a competitor within a defined distance of the target store location;
receiving via the communication network existing store data associated with a plurality of existing stores;
performing a clustering technique based on the target store location data and the existing store data, the clustering technique using at least population growth data associated with the target store location and the plurality of existing stores, wherein the population growth data is normalized for the clustering technique;
based on the clustering technique, determining a peer selection group comprising a group of stores determined to have similar attributes to the target store location;
determining sales distortions for a plurality of divisions associated with the group of stores in the peer selection group;
generating a distortion matrix comprising a ranked list of the plurality of divisions; and
causing a user interface to present a merchandise mix recommendation for the target store location, the merchandise mix recommendation determined based on the distortion matrix, the merchandise mix specifying a percentage of a total budget to be used in departments of the target store location, which correspond to the plurality of divisions, the user interface further caused to present on a display device a geographical map with graphical legends representing the target store location, the plurality of existing stores, and the group of stores in the peer selection group,
wherein the determining sales distortions includes at least determining a performance index per division in the plurality of divisions as a ratio of the division's sales percentage in the peer selection group and the division's sales percentage for all stores.

2. The method of claim 1 , further comprising:
automatically selecting the merchandise mix recommendation and performing a what-if-analysis to project a forecast of revenue associated with merchandising performed according to the merchandise mix recommendation; and
presenting the forecast of revenue via the user interface device.

3. The method of claim 1 , further comprising:
allowing a user to select the merchandise mix recommendation and performing a what-if-analysis to project a forecast of revenue associated with merchandising performed according to the merchandise mix recommendation; and
presenting the forecast of revenue via the user interface device.

4. The method of claim 1 , wherein the merchandise mix recommendation comprises recommending to maximize the division, responsive to determining that the performance index associated with the division is greater than a first threshold value.

5. The method of claim 1 , wherein the merchandise mix recommendation comprises recommending to consider merchandising based on a space constraint, responsive to determining that the performance index falls between a first threshold value and a second threshold value.

6. The method of claim 1 , wherein the merchandise mix recommendation comprises recommending to minimize the division responsive to determining that the performance index associated with the division is less than the second threshold value.

7. The method of claim 1 , wherein the network target store location data and the existing store data comprise demographic data.

8. A system providing causal performance analysis for store merchandising, comprising:
one or more hardware processors communicatively coupled to a communication network;
one or more of the hardware processors operable to receive via the communication network target store location data associated with a target store location, the target store location data including at least information associated with a competitor within a defined distance of the target store location;
one or more of the hardware processors further operable to receive via the communication network existing store data associated with a plurality of existing stores;
one or more of the hardware processors further operable to perform a clustering technique based on the target store location data and the existing store data, the clustering technique using at least population growth data associated with the target store location and the plurality of existing stores, wherein the population growth data is normalized for the clustering technique;
one or more of the hardware processors further operable to, based on the clustering technique, determine a peer selection group comprising a group of stores determined to have similar attributes to the target store location;
one or more of the hardware processors further operable to determine sales distortions for a plurality of divisions associated with the group of stores in the peer selection group;
one or more of the hardware processors further operable to generate a distortion matrix comprising a ranked list of the plurality of divisions;
one or more of the hardware processors further operable to cause to present via a user interface, a merchandise mix recommendation for the target store location, the merchandise mix recommendation determined based on the distortion matrix, the merchandise mix specifying a percentage of a total budget to be used in departments of the target store location, which correspond to the plurality of divisions, the user interface further caused to present on a display device a geographical map with graphical legends representing the target store location, the plurality of existing stores, and the group of stores in the peer selection group,
wherein one or more of the hardware processors are operable to determine sales distortions by determining performance index per division in the plurality of divisions as a ratio of the division's sales percentage in the peer selection group and division's sales percentage for all stores.

9. The system of claim 8 , wherein one or more of the hardware processors are further operable to automatically select the merchandise mix recommendation and perform a what-if-analysis to project a forecast of revenue associated with merchandising performed according to the merchandise mix recommendation, and present the forecast of revenue via the user interface device.

10. The system of claim 8 , wherein one or more of the hardware processors are further operable to allow a user to select the merchandise mix recommendation and perform a what-if-analysis to project a forecast of revenue associated with merchandising performed according to the merchandise mix recommendation, and present the forecast of revenue via the user interface device.

11. The system of claim 8 , wherein the merchandise mix recommendation comprises recommending to maximize the division, responsive to one or more of the hardware processors determining that the performance index associated with the division is greater than a first threshold value.

12. The system of claim 8 , wherein the merchandise mix recommendation comprises recommending to consider merchandising based on a space constraint, responsive to one or more of the hardware processors determining that the performance index falls between a first threshold value and a second threshold value.

13. The system of claim 8 , wherein the merchandise mix recommendation comprises recommending to minimize the division responsive to one or more of the hardware processors determining that the performance

Assignees

• IBM

Inventors

• Deshpande Ajay A
• Fei Hongliang
• Hampapur Arun
• Li Hongfei
• Liu Xuan

Classifications

• G06Q10/06393 Primary

  Score-carding, benchmarking or key performance indicator [KPI] analysis · CPC title

• G06Q10/06315

  Needs-based resource requirements planning or analysis · CPC title