Resumo

BRAVO ILISASTIGUI, Lisandra; MARTIN RODRIGUEZ, Diana  e  GARCIA BORROTO, Milton. A new method for not redundant Subgroup Discovery. Rev cuba cienc informat [online]. 2020, vol.14, n.3, pp. 18-40.  Epub 01-Set-2020. ISSN 2227-1899.

Subgroup Discovery is a Data Mining task to identify descriptions of subsets of a data set that show an interesting behavior with respect to certain interestingness criteria. A major problem that affect the comprehensibility of the results is the redundancy feature. Dependencies between the non-target attributes lead to large numbers of variations of a particular subgroup. Since many descriptions can have a similar coverage of the given data. In this work a new algorithm for the description induction of not overlapped subgroups (DINOS) is proposed. This algorithms is able to automatically determine the intervals for the numerical attributes of a data set. The experimental study shows that DINOS obtains subgroups with high quality that improves the results reported in the literatura.

Palavras-chave : Subgroup Discovery; redundancy; genetic algorithm.

        · resumo em Espanhol     · texto em Espanhol     · Espanhol ( pdf )