A New Credit Risk System Using Hybrid ELECTRE TRI and NSGA-II Methods

摘要: ELECTRE TRI is the most applicable and developed outranking based classification method in field of MCDA. By including a large number parameters, it provides huge amount information on criteria which enriches decision making process, although calculation these parameters very time consuming difficult task. To tackle this problem, paper proposes new called NSGA-ELECTRE, by NSGA-  algorithm learns elicits its through an evolutionary process. The proposed contributes to literature utilizing pair conflicting objective functions Type I errors II instead using single criterion named “classification accuracy” used frequently related works. ­­­The bi-objective applied six known credit risk datasets. NRGA model as benchmark for validation. Computational results indicate outstanding performance NSGA-ELECTRE method.