A hybrid methodology for learning belief networks: BENEDICT

Previous algorithms for the construction of belief networks structures from data are mainly based either on independence criteria or on scoring metric s. The aim of this paper is to present a hybrid methodology that is a combi nation of these two approaches, which benefits from characteristics of each one, and to develop two operative algorithms based on this methodology. Re sults of the evaluation of the algorithms on the well-known Alarm network a re presented, as well as the algorithms performance issues and some open pr oblems. (C) 2001 Elsevier Science Inc, All rights reserved.