A new tree-based approach for evaluating rule antecedent constraint in confabulation based association rule mining

摘要: Confabulation-based Association Rule Mining (CARM) is an algorithm that inspired by the thought process of human brain. It iterative method where, in each iteration, new rules are generated using a measure cogency and constraints on antecedents consequents previous iteration. This leads to particular ability dealing with rare items problem. Here, we aim study CARM's antecedent constraint respect pruning uninteresting rules. Hence, Tree-based CARM (TCARM) proposed which produces all only consequents. In our experiments, extracted these two algorithms compared those CFPGrowth several measures such as precision, recall, support approach finds association multiple minimum confidence, so can be used for evaluating TCARM. Our analysis based TCARM CFPGrowth, both synthetic real datasets, show prunes better than TCARM, confirms its help control number properly.