Using data mining technique to perform the performance assessment of lean service

Lean production and service means to improve the production and service management within an enterprise. Through several management techniques, the waste, the redundant things, and the expenses without added values can be cleared, and the production and service within an enterprise will become smoother, that is, the competitiveness of an enterprise will be enhanced. In this study, the data collected from experiment carried out in Toyota lean service simulation laboratory of China University of Technology are used for analysis. Data mining technique is used to investigate whether the result of lean production and service taken by enterprises can enhance the entire performance of production and service. In this study, Grey relational analysis is performed first and is used to judge whether the data collected in the experiment using lean production and service can enhance performance; then, clustering method is used to classify experimental data into two clusters based on service attitude and dish-serving efficiency; finally, three data mining techniques of Genetic Programming (GP), Back-propagation Artificial Neural Network and logistic regression are used to set up, respectively, lean service performance model and Employee Characteristic Analysis model. From the analysis result, it is shown that the result of lean production and service can indeed enhance the performance of entire production and service; and among the three data mining techniques, GP model has the best classification and forecast capability.