Visual Interactive Subgroup Discovery with Numerical Properties of Interest

Abstract. We propose an approach to subgroup discovery using distribution rules (a kind of association rules with a probability distribution on the consequent) for numerical properties of interest. The objective interest of the subgroups is measured through statistical goodness of fit tests. Their subjective interest can be assessed by the data analyst through a visual interactive subgroup browsing procedure. 1 Subgroup Discovery Subgroup discovery is an undirected data mining task, first identified by Klosgen [3], and meanwhile studied by others. A subgroup is a subset of a population having interesting values w.r.t. a property of interest. For example, if the average level cholesterol for all the patients of an hospital is 190, we may find interesting that people who smoke and drink have a cholesterol of around 250. In this case, we have a property of interest (the level of cholesterol) and a subgroup of patients with a precise description. This subgroup can be regarded as relevant o...

• Type: Conference
• Year: 2006
• Where: DIS
• Authors: Alípio Mário Jorge, Fernando Pereira 0002, Paulo J. Azevedo
• Keywords: DIS 2006, Discovery Subgroup, Subgroup Browsing Procedure, Subgroup Discovery, Theoretical Computer Science