An improved AHP and BP neural network method for service quality evaluation of city bus

Aimed at the realistic problem that service quality of city bus is low in big cities, an improved AHP-BP neural network method is established based on quality survey data of real passengers, in order to evaluate the analysis of quality factors. Firstly, the weight of each expert is worked out based on the perspectives of interests related for improving AHP, then the comprehensive weight of each index is determined by doing weighted average of obtained index weight of each expert and the corresponding evaluation weight of expert. Secondly, then the weight of the BP neural network is used to train and test the model based on the results of improved AHP, getting BP evaluation results with an acceptable error in order to promote the classifier system of service quality factors. Finally, an empirical research is carried for the example of service quality evaluation of city bus in Shenyang city of China. The results show that the method fully reflects the views of the experts with avoiding the conflicts of interest among experts, and reduces the arbitrariness of subjective evaluation; the learning ability of BP neural network model makes results more accurate and reliable. It illustrates the high application value of the improved AHP-BP neural network method in the evaluation of service quality of city bus in future.