RITIO - rule induction two in one
David Urpani, Xindong Wu, Jim Sykes · Knowledge Discovery and Data Mining · 1996
The identification of relevant attributes is an important and difficult task in data mining applications where induction is used as the primary tool for knowledge extraction. This paper introduces a new rule induction algorithm, RITIO, which eliminates attributes in order of decreasing irrelevancy. The rules produced by RITIO are shown to be largely based on only the most relevant attributes. Experimental results, with and without feature selection preprocessing, confirm that RITIO achieves high levels of predictive accuracy.