Multiple-Level Sequential Pattern Discovery from Customer Transaction Databases

Authors: An Chen, Huilin Ye

Abstract:

Mining sequential patterns from large customer transaction databases has been recognized as a key research topic in database systems. However, the previous works more focused on mining sequential patterns at a single concept level. In this study, we introduced concept hierarchies into this problem and present several algorithms for discovering multiple-level sequential patterns based on the hierarchies. An experiment was conducted to assess the performance of the proposed algorithms. The performances of the algorithms were measured by the relative time spent on completing the mining tasks on two different datasets. The experimental results showed that the performance depends on the characteristics of the datasets and the pre-defined threshold of minimal support for each level of the concept hierarchy. Based on the experimental results, some suggestions were also given for how to select appropriate algorithm for a certain datasets.

Keywords: Data Mining, Multiple-Level Sequential Pattern, Concept Hierarchy, Customer Transaction Database.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1057521

References:

[1] Chen, M.S., Han, J. and Yu, P.S., "Data Mining: An Overview from a Database Perspective," IEEE Transactions on Knowledge and Data Engineering, Vol. 8, No. 6, Dec, 1996, pp. 866-883.
[2] Rakesh, A., Tomasz, I. and Arun, S., "Mining Association Rules Between Sets of Items in Large Databases," ACM SIGMOD, May 1993, pp. 207-216.
[3] Park, J.S., Chen, M.S., and Yu, P.S., "An Effective Hash Bashed Algorithm for Mining Association Rules," in Proceedings of ACM SIGMOD, May 1995, pp. 175-186.
[4] Rakesh, A. and Ramakrishnan, S., "Fast Algorithm for Mining Association Rules," in Proceedings of 20th VLDB Conference, Santiago, Chile, 1994, pp. 487-499.
[5] Chen, N. and Chen, A., "Discovery of Multiple-Level Sequential Patterns from Large Databases," in Proceedings of the 4th International Symposium On Future Software Technology (ISFST-1999), Oct. 27-29, 1999, Nanjing, P. R. China, pp. 169-174.
[6] Rakesh, A. and Ramakrishnan, S., "Mining Sequential Patterns," Research Report, RJ 9910, IBM Almaden Research Center, San Jose, California, October 1994.
[7] Han, J., and Fu, Y., "Discovery of Multiple-Level Association Rules from Large Databases," in Proceedings of 21st VLDB Conference, Zurich, Switzerland, 1995, pp. 420-431.
[8] Ramakrishnan, S. and Rakesh, A., "Mining Generalized Association Rules," in Proceedings of 21st VLDB Conference, Zurich, Switzerland, 1995, pp. 407-419.
[9] Rakesh, A. and Ramakrishnan, S., "Mining Sequential Patterns," in Proceedings of the 11th International Conference on Data Engineering, March 1995, Taipei, Taiwan, IEEE Computer Society, pp. 3-14.
[10] Chen, R.S., Tzeng, G.H., Chen, C.C. and Hu, Y.C., "Discovery of Fuzzy Sequential Patterns for Fuzzy Partitions in Quantitative Attributes," in Proceedings of ACS/IEEE International Conference on Computer Systems and Applications (AICCSA'01), June, 2001, Beirut, Lebanon, pp. 144-150.