Application of Artificial Neural Networks to Identify Customers Satisfied with Car After Sales Services

Abstract

The purpose of the research was the development of a neural networks model to identify satisfied customers for car maintenance service marketing. The data were collected from the survey of ten car maintenance service providers in Iran. Multi-layer perceptron (MLP) neural networks with hyperbolic tangent function trained by feed forward training algorithm were utilized to build the identification model. The result reveals that the identification accuracy of the test on the model is greater than that expected by chance. Through a set of available contribution weights, the general importance of each independent variable produced is revealed. This research confirms that the neural network model is useful in recognizing the existing patterns of customer’s data. The advantages of using the model are highlighted. Authors believe that the model is useful and suitable as an analyzing tool for car maintenance service on market strategy planning.

Keywords

• car after sales services
• mlp neural networks
• marketing strategy
• customer satisfaction