The FEDHC Bayesian Network Learning Algorithm

The paper proposes a new hybrid Bayesian network learning algorithm, termed Forward Early Dropping Hill Climbing (FEDHC), devised to work with either continuous or categorical variables. Further, the manifests that only implementation of MMHC in statistical software R is prohibitively expensive, and offered. specifically for case data, robust outliers version FEDHC, which can be adopted by other BN algorithms, proposed. FEDHC tested via Monte Carlo simulations distinctly show it computationally efficient, produces networks similar to, higher accuracy than PCHC. Finally, an application PCHC algorithms real from field economics, demonstrated using R.