Augmented semi-naive Bayes classifier

The naive Bayes is a competitive classifier that makes strong conditional independence assumptions. Its accuracy can be improved by relaxing these assumptions. One classifier which does that is the semi-naive Bayes. The state-of-the-art algorithm for learning a semi-naïve Bayes from data is the backward sequential elimination and joining (BSEJ) algorithm. We extend BSEJ with a second step which removes some of its unwarranted independence assumptions. Our classifier out performs BSEJ and five other Bayesian network classifiers on a set of benchmark databases, although the difference in performance is not statistically significant