RSD: Relational Subgroup Discovery through First-Order Feature Construction

Relational rule learning is typically used in solving classi- fication and prediction tasks. However, relational rule learning can be adapted also to subgroup discovery. This paper proposes a proposition- alization approach to relational subgroup discovery, achieved through appropriately adapting rule learning and first-order feature construction. The proposed approach, applicable to subgroup discovery in individual- centered domains, was successfully applied to two standard ILP problems (East-West trains and KRK) and a real-life telecommunications applica- tion.