Mining generalised disjunctive association rules

作者: Amit A. Nanavati , Krishna P. Chitrapura , Sachindra Joshi , Raghu Krishnapuram

DOI: 10.1145/502585.502666

关键词:

摘要: This paper introduces generalised disjunctive association rules such as "People who buy bread also butter jam", and either raincoats or umbrellas flashlights". A rule allows the disjunction of conjuncts, jackets bow ties neckties tiepins". Such capture contextual inter-relationships among items.Given a context (antecedent), there may be large number that satisfy minsupp minconf constraints. It is computationally expensive to find all rules. We present algorithm thrifty traverse which borrows concepts subsumption from propositional logic mine subset in feasible way. experimented with our on US census data well transaction grocery superstore demonstrate its computational feasibility, utility scalability.

参考文章(23)
Heikki Mannila, A. Inkeri Verkamo, Hannu Toivonen, Efficient algorithms for discovering association rules knowledge discovery and data mining. pp. 181- 192 ,(1994)
Stefanos Manganaris, Ramakrishnan Srikant, Kamal Ali, Partial classification using association rules knowledge discovery and data mining. pp. 115- 118 ,(1997)
Mehran Sahami, Daphne Koller, Using machine learning to improve information access Stanford University. ,(1998)
Alex Cheskis, Boris Levin, Abraham Meidan, Pattern recognition using generalized association rules ,(1998)
Sholom M. Weiss, Nitin Indurkhya, Lightweight Rule Induction international conference on machine learning. pp. 1135- 1142 ,(2000)
Ramakrishnan Srikant, Rakesh Agrawal, Mining Generalized Association Rules very large data bases. pp. 407- 419 ,(1995)
Ramakrishnan Srikant, Quoc Vu, Rakesh Agrawal, Mining association rules with item constraints knowledge discovery and data mining. pp. 67- 73 ,(1997)
Heikki Mannila, Sanjeev Saluja, Dimitrios Gunopulos, Discovering All Most Specific Sentences by Randomized Algorithms international conference on database theory. pp. 215- 229 ,(1997)