A new integrated approach for ranking and clustering of credit customer (Case study: A large bank in Iran)

This study presents an integrated intelligent algorithm for ranking credit customer in different industry sections. The algorithm has two basic modules that is A2 method which suggested by Hosseininasab et al in 2012 and data envelopment analysis (DEA) with three phases: design, execution and performance assessment. In the design phase, a hierarchical structure of the problem based on A2-DEA method (artificial neural network (ANN), Analytical Hierarchy Process (AHP) and DEA) is built and different criteriaʹs are determined based on reviewing of literature. In the execution phase, the proposed method is tested by real data of large bank in Iran. Finally, performance assessment of proposed method is done in third phases. To show the applicability and superiority of the proposed algorithm, two hundred customers of a large bank in different industry sections are studied. This is the first study that uses present an integrated intelligent algorithm for ranking credit customers. This proposed method is compared with A2 method separately. The implementation results show that this method is significantly valid for ranking credit customers.Comparison of methods shows that although AHP and DEA have benefits, they also suffer from limitations, which can be avoided by the A2-DEA model, also improves the time and cost needed for implementing in comparison.