High Confidence Association Mining Without Support Pruning

  • Ramkishore Bhattacharyya
  • Balaram Bhattacharyya
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4815)

Abstract

High confidence associations are of utter importance in knowledge discovery in various domains and possibly exist even at lower threshold support. Established methods for generating such rules depend on mining itemsets that are frequent with respect to a pre-defined cut-off value of support, called support threshold. Such a framework, however, discards all itemsets below the threshold and thus, existence of confident rules below the cut-off is out of its purview. But, infrequent itemsets can potentially generate confident rules. In the present work we introduce a concept of cohesion among items and obtain a methodology for mining high confidence association rules from itemsets irrespective of their support. Experiments with real and synthetic datasets corroborate the concept of cohesion.

Keywords

Association rule high-confidence support threshold cohesion 

References

  1. 1.
    Aggarwal, R., Imielinski, T., Swami, A.: Mining Association Rules between Sets of Items in Large Databases. In: Proceedings of ACM SIGMOD 1993, Washington DC, pp. 207–216 (1993)Google Scholar
  2. 2.
    Aggarwal, R., Srikant, R.: Fast Algorithm for Mining Association Rules. In: VLDB. Proceedings of 20th Very Large Database Conf., pp. 487–499 (1994)Google Scholar
  3. 3.
    Cohen, E., Datar, M., Fujiwara, S., Gionis, A., Indyk, P., Motwani, R., Ullman, J.D., Yang, C.: Finding Interesting Associations without Support Pruning. In: Proceedings of IEEE ICDE, pp. 489–500 (2000)Google Scholar
  4. 4.
    Jinyan, L., Xiuzhen, Z., Guozhu, D., Kotagiri, R., Qun, S.: Efficient Mining of High Confidence Association Rules without Support Thresholds. In: Żytkow, J.M., Rauch, J. (eds.) PKDD 1999. LNCS (LNAI), vol. 1704, pp. 406–411. Springer, Heidelberg (1999)Google Scholar
  5. 5.
    Pal, S., Bagchi, A.: Association against Dissociation: some pragmatic considerations for Frequent Itemset generation under Fixed and Variable Thresholds. SIGKDD Explorations 7(2), 151–159 (2005)CrossRefGoogle Scholar
  6. 6.
    Zaki, M.J.: Scalable Algorithms for Association Rule Mining. IEEE Trans. On Knowledge and Data Engg 12(3), 372–390 (2000)CrossRefMathSciNetGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2007

Authors and Affiliations

  • Ramkishore Bhattacharyya
    • 1
  • Balaram Bhattacharyya
    • 2
  1. 1.Microsoft India (R&D) Pvt. Ltd., Gachibowli, Hyderabad - 500 032India
  2. 2.Dept of Computer and System Sciences, Visva-Bharati Universty, Santiniketan – 731235India

Personalised recommendations