Systems and methods for mining transactional and time series data

• US 7,711,734 B2
• Filed: 04/05/2007
• Issued: 05/04/2010
• Est. Priority Date: 04/06/2006
• Status: Active Grant

• Current Assignee: SAS Institute Incorporated
• Original Assignee: SAS Institute Incorporated
• Inventors: Leonard, Michael James
• Primary Examiner(s): Vital; Pierre M
• Assistant Examiner(s): Kim; Taelor
• Application Number:
  US11/696,951
• Publication Number:
  US 20070239753A1
• Time in Patent Office: 1,125 Days
• Field of Search: None
• US Class Current: 707/736
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising

Abstract

In accordance with the teachings described herein, systems and methods are provided for analyzing transactional data. A similarity analysis program may be used that receives time-series data relating to transactions of an organization and performs a similarity analysis of the time-series data to generate a similarity matrix. A data reduction program may be used that receives the time-series data and performs one or more dimension reduction operations on the time-series data to generate reduced time-series data. A distance analysis program may be used that performs a distance analysis using the similarity matrix and the reduced time-series data to generate a distance matrix. A data analysis program may be used that performs a data analysis operation, such as a data mining operation, using the distance matrix to generate a data mining analysis of the transactional data.

Claims

1. A computer implemented method for generating a data mining analysis of transactional data, comprising:

receiving, on one or more processors, time-variant time-series data relating to transactions of an organization;

accumulating the time-variant time-series data into a plurality of time-series vectors;

using the plurality of time-series vectors to concurrently perform a plurality of dimension reduction operations upon the time-variant time-series data and a similarity analysis upon the time-variant time-series data, wherein performing the plurality of dimension reduction operations generates reduced time-variant time-series data, and wherein performing the similarity analysis generates a similarity matrix;

combining the similarity matrix and the reduced time-variant time-series data into a data matrix;

performing a distance analysis using the data matrix to generate a distance matrix;

performing a data mining operation using the distance matrix to generate the data mining analysis of the transactional data; and

storing the data mining analysis in a computer-readable medium.

2. The method of claim 1, further comprising:

receiving time-stamped transactional data; and

accumulating the time-stamped transactional data to generate the time-variant time-series data.

3. The method of claim 1, wherein the plurality of dimension reduction operations includes a seasonal adjustment and decomposition analysis.

4. The method of claim 1, wherein the plurality of dimension reduction operations includes a component analysis.

5. The method of claim 1, wherein the plurality of dimension reduction operations includes a time domain analysis.

6. The method of claim 1, wherein the plurality of more dimension reduction operations includes a frequency domain analysis.

7. The method of claim 1, wherein the plurality of dimension reduction operations includes fitting the time-variant time-series data to a time-series model.

8. The method of claim 1, wherein the data mining operation is a clustering analysis.

9. The method of claim 1, wherein the data mining operation is a sampling analysis.

10. The method of claim 1, wherein the data mining operation is a data classification.

11. The method of claim 1, wherein the data mining operation is a decision tree.

12. The method of claim 1, further comprising:

smoothing the time-variant time-series data prior to performing the similarity analysis.

13. The method of claim 1, wherein the data matrix is a series properties matrix.

14. A system for generating a data mining analysis of transactional data, comprising:

one or more processors;

one or more computer-readable storage mediums containing instructions operable to cause the one or more processors to perform operations including;

receiving time-variant time-series data relating to transactions of an organization;

accumulating the time-variant time-series data into a plurality of time-series vectors;

using the plurality of time-series vectors to concurrently perform a plurality of dimension reduction operations upon the time-variant time-series data and a similarity analysis upon the time-variant time-series data, wherein performing the plurality of dimension reduction operations generates reduced time-variant time-series data, and wherein performing the similarity analysis generates a similarity matrix;

combining the similarity matrix and the reduced time-variant time-series data into a data matrix;

performing a distance analysis using the data matrix to generate a distance matrix; and

performing a data mining operation using the distance matrix to generate the data mining analysis of the transactional data.

15. The system of claim 14, further comprising:

receiving time-stamped transactional data; and

accumulating the time-stamped transactional data to generate the time-variant time-series data.

16. The system of claim 14, wherein the plurality of dimension reduction operations includes a seasonal adjustment and decomposition analysis.

17. The system of claim 14, wherein the plurality of dimension reduction operations includes a component analysis.

18. The system of claim 14, wherein the plurality of dimension reduction operations includes a time domain analysis.

19. The system of claim 14, wherein the plurality of dimension reduction operations includes a frequency domain analysis.

20. The system of claim 14, wherein the plurality of dimension reduction operations includes fitting the time-variant time-series data to a time-series model.

21. The system of claim 14, wherein the data mining operation is a clustering analysis.

22. The system of claim 14, wherein the data mining operation is a sampling analysis.

23. The system of claim 14, wherein the data mining operation is a data classification.

24. The system of claim 14, wherein the data mining operation is a decision tree.

25. The system of claim 14, further comprising:

smoothing the time-variant time-series data prior to performing the similarity analysis.

26. The system of claim 14, wherein the data matrix is a series properties matrix.

27. The system of claim 14, wherein the similarity analysis is a dynamic time warping analysis.

28. The system of claim 14, wherein the similarity analysis is a derivative dynamic time warping analysis.

29. The system of claim 14, wherein the similarity analysis is a least common subsequence similarity analysis.

30. A computer-readable storage medium encoded with instructions that when executed, cause a computer to perform a data mining analysis method, comprising:

receiving time-variant time-series data relating to transactions of an organization;

accumulating the time-variant time-series data into a plurality of time-series vectors;

using the plurality of time-series vectors to concurrently perform a plurality of dimension reduction operations upon the time-variant time-series data and a similarity analysis upon the time-variant time-series data, wherein performing the plurality of dimension reduction operations generates reduced time-variant time-series data, and wherein performing the similarity analysis generates a similarity matrix;

combining the similarity matrix and the reduced time-variant time-series data into a data matrix;

performing a distance analysis using the data matrix to generate a distance matrix;

performing a data mining operation using the distance matrix to generate the data mining analysis of the transactional data; and

storing the data mining analysis.

31. A computer implemented method for generating a data mining analysis of transactional data, comprising:

receiving, on one or more processors, time-variant time-series data relating to transactions of an organization;

accumulating the time-variant time-series data into a plurality of time-series vectors;

using the plurality of time-series vectors to concurrently perform a plurality of dimension reduction operations upon the time-variant time-series data and a similarity analysis upon the time-variant time-series data, wherein performing the plurality of dimension reduction operations generates reduced time-variant time-series data, and wherein performing the similarity analysis of the time-variant time-series data includes preparing the time-variant time-series data and then applying dynamic time warping to the prepared time-variant time-series data to generate a similarity matrix;

combining the similarity matrix and the reduced time-variant time-series data into a data matrix;

performing a distance analysis using the data matrix to generate a distance matrix; and

performing a data mining operation using the distance matrix to generate the data mining analysis of the transactional data.