Fuzzy Apriori Rule Extraction Using Multi-Objective Particle Swarm Optimization: The Case of Credit Scoring

There are many methods introduced to solve the credit scoring problem such assupport vector machines, neural networks and rule based classifiers. Rule bases aremore favourite in credit decision making because of their ability to explicitlydistinguish between good and bad applicants.In this paper multi-objective particleswarm is applied to optimize fuzzy apriori rule base in credit scoring. Differentsupport and confidence parameters generate different rule bases in apriori.Therefore Multi-objective particle swarm is used as a bio-inspired technique tosearch and find fuzzy support and confidence parameters, which gives the optimumrules in terms of maximum accuracy, minimum number of rules and minimumaverage length of rule. Australian, Germany UCI and a real Iranian commercialbank datasets is used to run the algorithm. The proposed method has shown betterresults compared to other classifiers.

Fuzzy Apriori Rule Extraction Using Multi-Objective Particle Swarm Optimization: The Case of Credit Scoring Keywords:

Credit scoring , Banking , Fuzzy association rules , Apriori , multi-objective particle swarm