Presenting a predictive benchmark model of after-sales service agencies for vehicles based on the data envelopment analysis approach

Abstract

Everyone is aware of the importance of benchmarking in all industries. The same is true of the automotive industry. One of the methods of continuous improvement of car after-sales service agencies is benchmarking from successful and efficient examples in the country. Given that evaluation and benchmarking methods are usually retrospective, and also, the rapid changes in environment and customer needs, current methods cannot quickly define corrective actions. In this paper, first, a benchmarking model based on data envelopment analysis is developed for car after-sales service dealers as decision-making units, then considering that the model outputs have a high correlation coefficient, an innovative machine learning model has been used to predict the outputs. Finally, the results of the proposed prediction model are compared with a perceptron neural network algorithm. The results show that the benchmarking and prediction model together with a 7.7% error predicts benchmarks for the end of current period.