This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
ExAnte: A Preprocessing Method for Frequent-Pattern Mining
May/June 2005 (vol. 20 no. 3)
pp. 25-31
Francesco Bonchi, Knowledge Discovery and Delivery Laboratory
Fosca Giannotti, Knowledge Discovery and Delivery Laboratory
Alessio Mazzanti, Knowledge Discovery and Delivery Laboratory
Dino Pedreschi, Knowledge Discovery and Delivery Laboratory
ExAnte is a simple yet effective approach for preprocessing input data for mining frequent patterns. The approach questions established research in that it requires no trade-off between antimonotonicity and monotonicity. Indeed, ExAnte relies on a strong synergy between these two opposite components and exploits it to dramatically reduce the data being analyzed to that containing interesting patterns. This data reduction, in turn, induces a strong reduction of the candidate patterns' search space. The result is significant performance improvements in subsequent mining. It can also make feasible some otherwise intractable mining tasks. The authors describe their technology and experiments that proved its effectiveness using different constraints on various data sets.
Index Terms:
frequent-pattern mining, constraints, preprocessing, data reduction
Citation:
Francesco Bonchi, Fosca Giannotti, Alessio Mazzanti, Dino Pedreschi, "ExAnte: A Preprocessing Method for Frequent-Pattern Mining," IEEE Intelligent Systems, vol. 20, no. 3, pp. 25-31, May-June 2005, doi:10.1109/MIS.2005.45
Usage of this product signifies your acceptance of the Terms of Use.