METHOD AND SYSTEM UTILIZING ONLINE ANALYTICAL PROCESSING (OLAP) FOR MAKING PREDICTIONS ABOUT BUSINESS LOCATIONS

• US 20080208652A1
• Filed: 09/10/2007
• Published: 08/28/2008
• Est. Priority Date: 02/23/2007
• Status: Active Grant

• Current Assignee: Saama Technologies LLC (Saama Technologies, Inc.)
• Original Assignee: Saama Technologies, Inc.
• Inventors: Srivastava, Ashok N.
• Granted Patent: US 7,774,227 B2
• Time in Patent Office: Days
• US Class Current: 705/7
• 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 10/06375 Prediction of business process outcome or impact based on a proposed change
• CPC Class Codes: G06Q 30/0205 Location or geographical consideration

Abstract

A method and system that utilizes OLAP and supporting data structures for making predictions about business locations. The method includes providing a spatial map and analyzing heterogeneous data having a spatial component to find utilizable data. Relationships are automatically extracted from the utilizable data by employing machine learning. The step of automatically extracting relationships includes generating a composite indicator, which correlates spatial data with unstructured data. The extracted relationships are presented on a spatial map to make a prediction about at least one business location. Preferably, the predictions are presented as a rank-ordered list on the spatial map and a heat map overlays the spatial map to indicate predictions about particular regions.

Claims

1. A method for making predictions about business locations, comprising the steps of:

providing a spatial map;

analyzing heterogeneous data having a spatial component to find utilizable data and storing the utilizable data in an OLAP graph data structure;

extracting relationships from the utilizable data;

using the extracted relationships to make a prediction about at least one business location; and

presenting the prediction on the spatial map.

2. A method as set forth in claim 1, wherein the prediction is presented as a rank-ordered list on the spatial map.

3. A method as set forth in claim 1, wherein the spatial map includes a heat map.

4. A method as set forth in claim 3, wherein the step of presenting includes displaying polygons of various colors.

5. A method as set forth in claim 1, wherein the step of extracting relationships includes generating a composite indicator.

6. A method as set forth in claim 5, wherein the composite indicator correlates spatial data with unstructured data and structured data.

7. A method as set forth in claim 1, wherein the composite indicator correlates the spatial data with at least one indicator derived from the group consisting essentially of:

demographic variables, competitor proximity, accessibility, product mix, and comparable customer spending patterns.

8. A method as set forth in claim 1, wherein the step of extracting relationships includes the step of adaptive machine learning.

9. A method as set forth in claim 1, wherein the step of analyzing includes creating a data matrix having a particular dimensionality and the method further comprises the step of reducing the dimensionality of the data matrix.

10. A method as set forth in claim 1, wherein the step of analyzing includes creating a data matrix having a particular dimensionality and the method further comprises the step of reducing the dimensionality of the data matrix by assigning relevancy scores to the data, selecting meaningful data based on the relevancy score and utilizing only the meaningful data.

11. A method as set forth in claim 1, wherein the step of extracting relationships includes extracting relationships using correlation analysis.

12. A method as set forth in claim 1, wherein the data structure is a SOLAP-graph data structure or an MOLAP-graph data structure or HOLAP-graph data structure.

13. A system for making predictions about business locations, comprising:

a data analyzer having an interface for displaying a spatial map;

databases in communication with the data analyzer, the databases including heterogeneous data having a spatial component;

the data analyzer analyzes the heterogeneous data component to find utilizable data, extracts relationships from the utilizable data;

stores the utilizable data in an OLAP data structure; and

uses the extracted relationships to make a prediction about at least one business location, and

the interface displays the prediction on the spatial map.

14. A system as set forth in claim 13 wherein the interface displays the prediction in the form of a rank-ordered list.

15. A system as set forth in claim 13 wherein the spatial map includes a heat map and the interface displays the prediction on the heat-map to predict optimal regions for a business location.

16. A system as set forth in claim 15, wherein the heat-map includes polygons of various colors.

17. A system as set forth in claim 13, wherein the data analyzer generates a composite indicator to extract relationships.

18. A system as set forth in claim 13, wherein the data analyzer generates a composite indicator to extract relationships, the composite indicator correlates spatial data with unstructured data and structured data.

19. A system as set forth in claim 13, wherein the data analyzer generates a composite indicator to extract relationships, the composite indicator correlates spatial data with an indicator derived from the group consisting essentially of:

demographic variables, competitor proximity, accessibility, product mix, and comparable customer spending patterns.

20. A system as set forth in claim 13, wherein the data analyzer employs adaptive machine learning for extracting relationships from the utilizable data.

21. A system as set forth in claim 13, wherein the data analyzer creates a data matrix having a particular dimensionality and reduces the dimensionality of the data matrix.

22. A system as set forth in claim 13, wherein the data analyzer creates a data matrix having a particular dimensionality and reduces the dimensionality of the data matrix by assigning relevancy scores to the data, selecting meaningful data based on the relevancy score and utilizing only the meaningful data.

23. A system as set forth in claim 13, wherein the data analyzer extracts relationships using correlation analysis.

24. A method for identifying profitability drivers for a business, comprising the steps of:

providing a spatial map;

analyzing heterogeneous data having a spatial component to find utilizable data;

storing the utilizable data in a OLAP data structure;

automatically extracting composite indicators from the utilizable data; and

making a prediction using the composite indicators about at least one profitability driver for at least one business location.

25. A method as set forth in claim 24, further comprising:

presenting the prediction in the form of a rank-ordered list of profitability drivers and profitability inhibitors.

26. A method as set forth in claim 24, further comprising:

presenting a heat-map to display regions having optimal profitability drivers.

27. A method as set forth in claim 24, wherein presenting a heat-map includes displaying polygons of various colors.

28. A computer system comprising:

a processing unit; and

a memory coupled to the processor, the memory having stored therein a code for performing the steps of;

providing a spatial map;

analyzing heterogeneous data having a spatial component to find utilizable data and storing the utilizable data in an OLAP data structure;

extracting relationships from the utilizable data;

using the extracted relationships to make a prediction about at least one business location; and

presenting the prediction on the spatial map.

29. A computer-readable medium operable with a computer system, the computer-readable medium having stored instructions for performing the steps of:

providing a spatial map;

analyzing heterogeneous data having a spatial component to find utilizable data and storing the utilizable data in an OLAP data structure;

extracting relationships from the utilizable data;

using the extracted relationships to make a prediction about at least one business location; and

presenting the prediction on the spatial map.

30. A computer readable medium as set forth in claim 29, wherein the computer readable medium is implemented in hardware.

31. A computer readable medium as set forth in claim 29, wherein the computer readable medium is implemented in firmware.

32. A computer readable medium as set forth in claim 29, wherein the computer readable medium is implemented in software.