Mining first-order maximal frequent patterns

Warning

This publication doesn't include Institute of Computer Science. It includes Faculty of Informatics. Official publication website can be found on muni.cz.

Authors	BLAŤÁK Jan POPELÍNSKÝ Lubomír
Year of publication	2004
Type	Article in Periodical
Magazine / Source	Neural Network World
MU Faculty or unit	Faculty of Informatics
Citation
Field	Informatics
Keywords	knowledge discovery in databases; inductive logic programming; frequent patterns; feature construction; propositionalization
Description	Frequent patterns discovery is one of the most important data mining tasks. We introduce RAP, the first system for finding first-order maximal frequent patterns. We describe search strategies and methods of pruning the search space. RAP generates long patterns much faster than other systems.RAP has been used for feature construction for propositional as well as multirelational data. We prove that partial search for maximal frequent patterns as new features is competitive with other approaches and results in classification accuracy increase.
Related projects:	Human-computer interaction, dialog systems and assistive technologies