Modeling and analysis of bank customer satisfaction using neural networks approach

Abstract

Purpose – The purpose of this paper is to propose the application of artificial neural networks (ANN) to predict overall bank customer satisfaction and to prioritize influencing factors on customer satisfaction. Design/methodology/approach – Data are collected from 436 randomly selected customers at ten different branches of an Iranian bank using a questionnaire consisting of 51 questions. An exploratory factor analysis (EFA) is done on the collected data to determine those factors that influence customer satisfaction. A multilayer perceptron ANN model is developed using the factor scores from the EFA. The ANN model is trained and validated to predict overall bank customer satisfaction. In addition, a linear regression model is developed to predict customer satisfaction. Prediction accuracy of the ANN model is compared with that of the linear regression model. The developed ANN is then used to compare sensitivity of customer satisfaction to each influencing factor. Findings – Nine different influencing factors are extracted by EFA. The factors include Fees and Loans, Prompt Service, Appearance, Technological Service, Responsiveness, Reliability and Trustworthiness, Employees’ Attitudes and Behaviors, Accessibility to Bank and Availability of Service, and Interest Rates. Training and validation results show that the ANN model has 73 percent higher accuracy compared to the linear regression model in predicting overall bank customer satisfaction. Factor prioritization results show that Fees and Loans, Appearance, and Prompt Service have the highest impact on customer satisfaction, respectively; interest rate and accessibility to bank and availability of service are the least dominant factors influencing overall bank customer satisfaction. Practical implications – This study proposes a more reliable and accurate methodology to predict customer satisfaction when compared with regression-based methods. ANN can also be utilized by bank management systems to prioritize different influencing factors that affect the satisfaction level of bank customers. Originality/value – This paper advances the knowledge on bank customer satisfaction by proposing application of artificial intelligence methods. A case study is discussed and results of the application of an ANN are compared with those of a commonly used statistical regression model.

State-of-the-art in artificial neural network applications: A survey

“…This section highlights discusses, compares, summarizes and critiques more than eighty research articles on artificial neural network model's application to the diverse area of the economy. The comparison was made based on (i) author(s)/year of publication (ii) ANN modeling (iii) ANN area of application (iii) studied contribution to human challenges (with references to Supplementary Table 2) [ 11 , 119 , 120 , 121 , 122 , 123 , 124 , 125 , 126 , 127 , 128 , 129 , 130 , 131 , 132 , 133 , 134 , 135 , 136 , 137 , 138 , 139 , 140 , 141 , 142 , 143 , 144 , 145 , 146 , 147 , 148 , 149 , 150 , 151 , 152 , 153 , 154 , 155 , 156 , 157 , 158 , 159 , 160 , 161 , 162 , 163 , 164 , 165 , 166 , 167 , 168 , 169 , 170 , 171 , 172 , 173 , 174 , 175 , 176 , 177 , 178 , …”

Comparison of the Resonant Frequency Determination of a Microstrip Patch Antenna using ANN and Analytical Methods

“…Artificial neural networks are computational models inspired from the structure and behavior of biological neurons and recently became a modeling and design tool that is an alternative of numerical models and analytical models [4]. The most used model of artificial neural networks nowadays is Multilayer perceptron (MLP) [15].…”

Application of Artificial Neural Network and Information Gain in Building Case-Based Reasoning for Telemarketing Prediction

“…The ability to classify the consumer behavior using machine learning techniques such as regression, non-linear principal component analysis and classification was demonstrated by Richard et al [3]. Modeling customer satisfaction has also resorted to ANN as its ability to determine the non-linear relationship between the consumer satisfaction and the factors that influence its behavior [4]. ANN is also used for volatile relationship like stock market on daily basis based on the index stock market indicator [5].…”