Monitoring Change in Mining Results
In the last years the datasets available have grown tremendously, and the development of efficient and scalable data mining algorithms has become a major research challenge. However, since the data is more dynamic than static there is also a strong need to update previously discovered rules and patterns. Recently, a couple of studies have emerged dealing with the topic of incremental update of discovered knowledge. These studies mostly concentrate on the question whether new rules emerge or old ones become extinct.
We present a framework that enables the analyst to monitor the changes a rule may undergo when the dataset the rules were discovered from is updated, and to observe emerging trends as data change. We propose a generic rule model that distinguishes between different types of pattern changes, and provide formal definitions for these. We present our approach in a case study on the evolution of web usage patterns. These patterns have been stored in a database and are used to observe the mining sessions as snapshots across the time series of a patterns lifetime.
KeywordsAssociation Rule Mining Session Mining Result Temporal Object Navigation Pattern
Unable to display preview. Download preview PDF.
- 1.N.F. Ayan, A.U. Tansel, and E. Arkun. An Efficient Algorithm To Update Large Itemsets With Early Pruning. In Proc. of the Fifth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pages 287–291, San Diego, CA, USA, August 1999. ACM.Google Scholar
- 2.S. Baron and M. Spiliopoulou. Monitoring the Results of the KDD Process: An Overview of Pattern Evolution. In J.M. Meij, editor, Converting Data into Knowledge, chapter 5. The Netherlands Study Center for Technology Trends, Den Haag, Netherlands, to appear in Sep. 2001.Google Scholar
- 3.S. Chakrabarti, S. Sarawagi, and B. Dom. Mining Surprising Patterns Using Temporal Description Length. In VLDB’98, pages 606–617, New York, USA, Aug. 1998. Morgan Kaufmann.Google Scholar
- 4.X. Chen and I. Petrounias. Mining Temporal Features in Association Rules. In Proceedings of the 3rd European Conference on Principles of Data Mining and Knowledge Discovery, pages 295–300, Prague, Czech Republic, September 1999. Springer.Google Scholar
- 5.D.W. Cheung, S.D. Lee, and B. Kao. A General Incremental Technique for Maintaining Discovered Association Rules. In DASFAA’97, Melbourne, Australia, Apr. 1997.Google Scholar
- 6.D.W. Cheung, V.T. Ng, and B.W. Tam. Maintenance of Discovered Knowledge: A Case in Multi-Level Association Rules. In KDD’96, 1996.Google Scholar
- 7.M. Ester, H.-P. Kriegel, J. Sander, M. Wimmer, and X. Xu. Incremental Clustering for Mining in a Data Warehousing Environment. In VLDB’98, pages 323–333, New York, USA, August 1998. Morgan Kaufmann.Google Scholar
- 8.R. Feldman, Y. Aumann, A. Amir, and H. Mannila. Efficient Algorithms for Discovering Frequent Sets in Incremental Databases. In DMKD’97, Tucson, USA, Mai 1997.Google Scholar
- 9.V. Ganti, J. Gehrke, and R. Ramakrishnan. A Framework for Measuring Changes in Data Characteristics. In Proceedings of the Eighteenth ACM SIGACT-SIGMOD-SIGART Symposium on Principles of Database Systems, pages 126–137, Philadelphia, USA, May 1999. ACM Press.Google Scholar
- 10.V. Ganti, J. Gehrke, and R. Ramakrishnan. DEMON: Mining and Monitoring Evolving Data. In Proceedings of the 15th International Conference on Data Engineering, pages 439–448, San Diego, USA, February 2000. IEEE Computer Society.Google Scholar
- 11.E. Omiecinski and A. Savasere. Efficient Mining of Association Rules in Large Databases. In BNCOD’98, pages 49–63, 1998.Google Scholar
- 12.M. Spiliopoulou. The Laborious Way from Data Mining to Web Mining. Int. Journal of Comp. Sys., Sci. & Eng., Special Issue on “Semantics of the Web”, 14:113–126, Mar. 1999.Google Scholar
- 13.M. Spiliopoulou and L.C. Faulstich. WUM: A Tool for Web Utilization Analysis. In EDBT Workshop WebDB’98, Valencia, Spain, Mar. 1998. Springer.Google Scholar
- 14.S. Thomas, S. Bodagala, K. Alsabti, and S. Ranka. An Efficient Algorithm for the Incremental Updation of Association Rules in Large Databases. In KDD-97, pages 263–266, Newport Beach, USA, Aug. 1997.Google Scholar
- 15.K. Wang. Discovering Patterns from Large and Dynamic Sequential Data. Intelligent Information Systems, 9:8–33, 1997.Google Scholar