Complex Decision Rules in DEX Methodology: Jrule Algorithm and Performance Analysis

DEX (Decision EXpert) is a qualitative multi-criteria decisionmodeling methodology. DEX models are used to evaluate and analyze decision alternatives. An essential component of DEX models are decision rules, represented in terms of decision tables. Decision tables may contain many elementary decision rules and may be difficult to be understood by the decision maker.A more compact and comprehensible representation is obtained by converting elementary decision rules to complex rules.The DEXRule algorithm, which is currently implemented in software DEXi, has been found inefficient with large decision tables.This research is aimed at improving the efficiency of the DEX-Rule algorithm.We propose a novel algorithm, called jRule, which generates complex rules by specialization.According to performance analysis, jRule is indeed more efficient than DEXRule.The compactness of complex rules produced by both algorithms varies and there is no clear winner.