The Study Of Power Customer Classification Based On Data Mining

The power customer classification can help Power Company understand its customer better, make different service strategies for different groups, satisfy the customer's requirement to the utmost and achieve mutual benefit between company and customer. Therefore, in this paper, the customer classification model which base on the data mining is established, the concept of constructing the data warehouse whose subject is customer classification is proposed, a customer classification index system which is based on the customer value is designed, Back Propagation Neural Network (BPNN)which is optimized by the Genetic Algorithm(GA)is provided, the problems of trapping into local minimum and low convergence speed which exists in the BPNN are solved. Finally, the result we use Matlab to classify the customer of Baoding Power Company proves the validity of the model.