Subgroup discovery is a problem in machine learning and data mining in which the population data is mined to discover interesting subgroups with respect to a target property. The goal of subgroup discovery is to find rules describing subsets of the population. In this paper, a new solving approach is proposed (FDG-SD). The new approach adopts fuzzy rule induction that uses a dynamic programming like algorithm to discover fuzzy subgroups. FDG-SD surpasses disadvantages of existing approaches. It is able to find better solutions for almost half out of 30 UCI machine learning repository datasets based on significance, unusualness, support, confidence and running time quality measures. According to Friedmann test results, the new approach (FDG-SD) is ranked first among mostly used algorithms with respect to significance, unusualness, support and running time quality measures.
IOS Press, Inc.
6751 Tepper Drive
Clifton, VA 20124
Tel.: +1 703 830 6300
Fax: +1 703 830 2300 firstname.lastname@example.org
(Corporate matters and books only) IOS Press c/o Accucoms US, Inc.
For North America Sales and Customer Service
West Point Commons
Lansdale PA 19446
Tel.: +1 866 855 8967
Fax: +1 215 660 5042 email@example.com