A Novel Ordering-Based Greedy Bayesian Network Learning Algorithm on Limited Data

Existing algorithms for learning Bayesian network (BN) require a lot of computation on high dimensional itemsets, which affects accuracy especially on limited datasets and takes up a large amount of time. To alleviate the above problem, we propose a novel BN learning algorithm OM- RMRG, Ordering-based Max Relevance and Min Redun- dancy Greedy algorithm. OMRMRG presents an ordering- based greedy search method with a greedy pruning proce- dure, applies Max-Relevance and Min-Redundancy feature selection method, and proposes Local Bayesian Increment function according to Bayesian Information Criterion (BIC) formula and the likelihood property of overfitting. Exper- imental results show that OMRMRG algorithm has much better efficiency and accuracy than most of existing BN learning algorithms on limited datasets.