A Kernel Density Estimation Based Interestingness Measure for Association Rule Mining

Abstract:

Association rules provide a concise statement of potentially useful information, and have been widely used in real applications. However, the usefulness of association rules highly depends on the interestingness measure which is used to select interesting rules from millions of candidates. In this study, a probability analysis of association rules is conducted, and a discrete kernel density estimation based interestingness measure is proposed accordingly. The new proposed interestingness measure makes the most of the information contained in the data set and obtains much lower falsely discovery rate than the existing interestingness measures. Experimental results show the effectiveness of the proposed interestingness measure.

• Periodical: Applied Mechanics and Materials (Volumes 20-23)
• Pages: 389-394
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.20-23.389
• Online since: January 2010
• Authors: Zhi Feng Hao, Rui Chu Cai, Tang Wu, Yi Yuan Zhou
• Keywords: Association Rule, Classification, Gene Expression Data, Interestingness Measure

References

[1] B. Liu, W. Hsu, and Y. Ma, Integrating Classification and Association Rule Mining, Proceeding of KDD Conference(1998), pp.80-86.

[2] Cheng, H., Yan, X., Han, J. & Yu, P.S. Direct Discriminative Pattern Mining for Effective Classification. Proceeding of ICDE Conference (2008), pp.169-178.

[3] G. Cong, A.K.H. Tung, X. Xu, F. Pan, and J. Yang, FARMER: Finding Interesting Rule Groups in Microarray Datasets, Proceeding of SIGMOD Conference(2004), pp.143-154.

DOI: 10.1145/1007568.1007587

[4] G. Cong, K. Tan, A.K.H. Tung, and X. Xu, Mining Top-k Covering Rule Groups for Gene Expression Data, Proceeding of SIGMOD Conference(2005) pp.670-681.

DOI: 10.1145/1066157.1066234

[5] J. Han and M. Kamber, Data Mining: Concepts and Techniques, Morgan Kaufmann(2000).

[6] Brin, S., Motwani, R., Ullman, J.D. & Tsur, S. Dynamic Itemset Counting and Implication Rules for Market Basket Data. Proceeding of SIGMOD Conference(1997), pp.255-264.

DOI: 10.1145/253262.253325

[7] Webb, G.I. Discovering significant rules. Machine Learning (2006), pp.434-443.

[8] J. Li, H. Li, L. Wong, J. Pei, and G. Dong, Minimum Description Length Principle: Generators Are Preferable to Closed Patterns, Proceeding of AAAI Conference, (2006).

[9] J. AITCHISON and C.G.G. AITKEN, Multivariate binary discrimination by the kernel method, Biometrika, vol. 63(1976), pp.413-420.

DOI: 10.1093/biomet/63.3.413

[10] P. HALL, On nonparametric multivariate binary discrimination, Biometrika, vol. 68(1981), pp.287-294.

DOI: 10.1093/biomet/68.1.287

[11] G. TUTZ, An alternative choice of smoothing for kernel-based density estimates in discrete discriminant analysis, Biometrika, vol. 73(1986), pp.405-411.

DOI: 10.1093/biomet/73.2.405

[12] C.F. Aliferis, I. Tsamardinos, A.R. Statnikov, and L.E. Brown, Causal Explorer: A Probabilistic Network Learning Toolkit for Biomedical Discovery, (2004).

[13] A.C. Tan, D.Q. Naiman, L. Xu, R.L. Winslow, and D. Geman, Simple decision rules for classifying human cancers from gene expression profiles, Bioinformatics, vol. 21(2005), pp.3896-3904.

DOI: 10.1093/bioinformatics/bti631

[14] R. Kohavi, A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection, Proceeding of IJCAI Conference(1995) pp.1145-1137.