A First Analysis of Qualitative Influences and Synergies

Comprehensibility is a key characteristic for learning algorithms results to be useful in Knowledge Discovery in Databases tasks. Bayesian reasoning has been usually criticized as hard to explain and understand, but achieves high performance rates with simple constructs, as happens for instance with the Naive-Bayes classifier. Our approach can be viewed as a refinement of qualitative probabilistic networks in order to allow them to do the work probabilistic networks do, or as a way of showing that, slightly modified, Elsaesser’s explanations can be used for reasoning and prediction, achieving results similar to Bayesian reasoning, while keeping intact their interpretability.