An Improved I-B & B-MDL-based Bayesian Network Learning Algorithm

Aiming at the hybrid algorithm I-B&B-MDL, an improved method is proposed. Firstly, it uses order-0 and partial order-1 independence tests to obtain an original Bayesian network structure. This reduces the number of independence tests and database passes while effectively restricting the search space. Secondly, it takes mutual information between nodes as heuristic knowledge perform sort order for candidate parent nodes, which increases the cut-offs of B&B search trees and accelerates the search process. The experimental results on the currency database show that the modified algorithm is quicker than some hybrid algorithms while keeping a high accuracy, and it can handle large data sets.