Measuring Credit Risk of Bank Customers Using Artificial Neural Network

Abstract

In many studies, the relationship between development of financial markets and economic growth has been proved. Credit risk is one of problems which banks are faced with it while doing their tasks. Credit risk means the probability of non-repayment of bank financial facilities granted to investors. If the credit risk decreases, banks will be more successful in performing their duties and have greater effect on economic growth of the country. Credit rating of customers and identifying good and bad customers, help banks lend to their good payers and hereby, they reduce probability of non-repayment. This paper aims to identify classification criteria for good customers and bad customers in Iranian banks. This study can classified in applied studies group and the research strategy is descriptive. Artificial neural network technique is used for financial facilities applicants' credit risk measurement and the calculations have been done by using SPSS and MATLAB software. Number of samples was 497 and 18 variables were used to identify good customers from bad customers. The results showed that, individual loan frequency and amount of loan had most important effect and also status of customer's bank account, history of customer relationship with bank and received services had least important effect in identifying classification criteria of good and bad customers. The major contribution of this paper is specifying the most important determinants for rating of customers in Iran's banking sector.

Predicting Customer Churn in Banking Industry using Neural Networks

“…It is powerful general-purpose software tool used for a number of data analysis tasks such as prediction, classification and clustering. Neural networks are used in finance such as portfolio management [18], credit rating [19] and predicting bankruptcy [20][21][22], forecasting exchange rates [23,24], predicting stock values [25,26], inflation [27] and cash forecasting [28] and others in order to achieve a reliable decisionmaking process through scientific approaches [29]. The ability of neural networks to discover nonlinear relationships in input data makes them ideal for modelling nonlinear dynamic systems such as banking industry.…”

Evaluation of the Credit Risk with Statistical analysis

“…Banks face problems such as the probability of non-repayment of received loans at the due date or nonrepayment that are called "credit risk" (Nazari & Alidadi 2013). Previous studies have illustrated that credit risk is widely studied topic in bank lending decisions and profitability (Angelini, di Tollo & Roli, 2008).…”

“…Generally, lenders do not have adequate data about the project to be finances; hence borrowers usually have proper information about those projects (Matoussi & Abdelmoula, 2009). A good legal customer with power of lending loans bring high profit for commercial banks, on the other hand bad legal customers who don't repay loans in due date, it will likely go bankrupt (Nazari & Alidadi 2013). There are various ways to predict credit risk such as probability and deterministic Simulation, Legit Analysis, Prohibit Analysis, Arbitrage Pricing Theory, Option Pricing Theory and linear probability model (Saunders and Allen, 2002).…”

Whose Balance Sheet Is This? Neural Networks for Banks' Pattern Recognition

“…First, given enough hidden layers and enough training samples, artificial neural networks can closely approximate any function, thus they are able to deal with non-linear relationships between factors in the data (see Bishop (1995), Han & Kamber (2006), Fioramanti (2008), Demyanyk & Hasan (2009), Eletter et al (2010), Sarlin (2014), and Hagan et al (2014)). Second, artificial neural networks make no assumptions about the statistical distribution or properties of the data (see Zhang et al (1999), McNelis (2005), Demyanyk & Hasan (2009), Nazari & Alidadi (2013), and Sarlin (2014)). Finally, particularly related to our objective, artificial neural networks have proven to be very effective classifiers, even better than the state-of-the-art models based on classical statistical methods (see Wu (1997), Zhang et al (1999), McNelis (2005), and Han & Kamber (2006)).…”

“…Similarly, artificial neural networks have been implemented to enhance loan decisions in the banking industry (see Angelini et al (2008), Eletter et al (2010), Nazari & Alidadi (2013), and Bekhet & Eletter (2014)). The general case is to classify borrowers' applications as good or bad based on non-payment records and a set of loan decision factors, which vary according to the type of borrower, namely a firm (e.g.…”