tailieunhanh - Valuation and assessment of customers in banking industry using data mining techniques

This paper uses Decision Tree, K-nearest neighbor (KNN), Support Vector Machine (SVM), Naive Bayes, and Logistic Regression for data categorization to estimate credit ranking of bank customers in one of major banks in Middle East. | Valuation and assessment of customers in banking industry using data mining techniques International Journal of Data and Network Science 3 2019 93 102 Contents lists available at GrowingScience International Journal of Data and Network Science homepage ijds Valuation and assessment of customers in banking industry using data mining techniques Behrooz Asareha and . Ghaelia a Department of Commerce and Business Administration New Westminster BC Canada CHRONICLE ABSTRACT Article history One of the primary concerns in most financial institutions to have an appropriate method for rank- Received September 17 2018 ing customers. Bank customers are the primary sources of creating income and the success of Received in revised format Octo- banking industry depends on how to select good customers for allocation of loans. This paper uses ber 29 2018 Decision Tree K-nearest neighbor KNN Support Vector Machine SVM Naive Bayes and Accepted December31 2018 Available online Logistic Regression for data categorization to estimate credit ranking of bank customers in one of December31 2018 major banks in Middle East. The results indicate that Logistic Regression was considered as the Keywords best method for ranking customers with the precision of while Decision Tree was consid- Data mining ered as the weakest technique with the precision of . Logistic regression Bank customer 2019 by the authors licensee Growing Science Canada. 1. Introduction Customers assessment is essential in providing a clear picture of the status and the ability of the client to timely fulfil their obligations preventing them from overuse of resources and falling into the financial crisis Bosch amp Steffen 2011 . Credit valuation is a process in which each borrower is assigned a quantity that represents an estimate of his her future performance in repaying his her loan Durand 1941 . Vali- dation models are mathematical models that according to the characteristics of the .