Credit Scoring of Bank Depositor with Clustering Techniques for Supply Chain Finance

Abstract

 Abstract- One of the natural consequences of lending practices by banks and credit institutions has been the creation of deferred and doubtful loans- a phenomenon that has become a major concern for these institutions and has had a negative impact on their revenue and expenditure.  From an internal perspective, operating costs, work efficiency, profitability, customer service, branch rank, employee wages and salaries, and other qualitative indicators are significantly affected. From an external perspective, these loans lead to slow cash flow, lack of timely and optimal allocation of resources to manufacturing networks and industries, low employment rates, and eventually economic recession. The purpose of this research is to cluster bank customers and determine the behavioral pattern of each cluster for supply chain finance using K-Means, FCM, and SUB Cluster models in Clementine 18.0, MATLAB 2016, and Excel software. 35 models were compared with a variety of parameters. After removing nonessential variables, the models were rerun and the outputs for each customer cluster were provided. The results showed that creditworthiness, education, job, collateral value, collateral type, loan term, and age respectively had the greatest impact. Finally, the K-Means model was found to be the most appropriate clustering technique.