Using sensitivity of a bayesian network to discover interesting patterns

In this paper, we present a new measure of interestingness to discover interesting patterns based on the user's background knowledge, represented by a Bayesian network. The new measure (Sensitivity measure) captures the sensitivity of the Bayesian network to the patterns discovered by assessing the uncertainty-increasing potential of a pattern on the beliefs of the Bayesian network. Patterns that attain the highest sensitivity scores are deemed interesting. In our approach, mutual information (from information theory) came in handy as a measure of uncertainty. The Sensitivity of a pattern is computed by summing up the mutual information increases incurred by a pattern when entered as evidence/findings to the Bayesian network. We demonstrate the strength of our approach experimentally using the KSL dataset of Danish 70 year olds as a case study. The results were verified by consulting two doctors (internists).

[1]  Margaret H. Dunham,et al.  Data Mining: Introductory and Advanced Topics , 2002 .

[2]  David J. Spiegelhalter,et al.  Bayesian analysis in expert systems , 1993 .

[3]  Judea Pearl,et al.  Probabilistic reasoning in intelligent systems - networks of plausible inference , 1991, Morgan Kaufmann series in representation and reasoning.

[4]  Abraham Silberschatz,et al.  On Subjective Measures of Interestingness in Knowledge Discovery , 1995, KDD.

[5]  Balaji Padmanabhan,et al.  A Belief-Driven Method for Discovering Unexpected Patterns , 1998, KDD.

[6]  Michael J. Shaw,et al.  Inductive learning for risk classification , 1990, IEEE Expert.

[7]  Claus Dethlefsen,et al.  deal: A Package for Learning Bayesian Networks , 2003 .

[8]  Sigal Sahar,et al.  Interestingness via what is not interesting , 1999, KDD '99.

[9]  Dan A. Simovici,et al.  Generating an informative cover for association rules , 2002, 2002 IEEE International Conference on Data Mining, 2002. Proceedings..

[10]  Rina Dechter,et al.  Bucket Elimination: A Unifying Framework for Reasoning , 1999, Artif. Intell..

[11]  Heikki Mannila,et al.  Finding interesting rules from large sets of discovered association rules , 1994, CIKM '94.

[12]  Tomasz Imielinski,et al.  Mining association rules between sets of items in large databases , 1993, SIGMOD Conference.

[13]  Wynne Hsu,et al.  Analyzing the Subjective Interestingness of Association Rules , 2000, IEEE Intell. Syst..

[14]  Szymon Jaroszewicz,et al.  Interestingness of frequent itemsets using Bayesian networks as background knowledge , 2004, KDD.

[15]  Aaas News,et al.  Book Reviews , 1893, Buffalo Medical and Surgical Journal.

[16]  Szymon Jaroszewicz,et al.  Fast discovery of unexpected patterns in data, relative to a Bayesian network , 2005, KDD '05.

[17]  Abraham Silberschatz,et al.  What Makes Patterns Interesting in Knowledge Discovery Systems , 1996, IEEE Trans. Knowl. Data Eng..

[18]  Jaideep Srivastava,et al.  Selecting the right interestingness measure for association patterns , 2002, KDD.

[19]  J. Ross Quinlan,et al.  Induction of Decision Trees , 1986, Machine Learning.

[20]  Wynne Hsu,et al.  Using General Impressions to Analyze Discovered Classification Rules , 1997, KDD.

[21]  Balaji Padmanabhan,et al.  Small is beautiful: discovering the minimal set of unexpected patterns , 2000, KDD '00.