The Research On Commercial Bank's Customer Segmentation Based On Data Mining

In recent years,customer relationship management has become a hot research.The customer relationship management of banks attracts the people's attention especially.Good customer relationship management can cut costs and bring huge profits for banks.The large amounts of data in the banks' database is a valuable asset.Banks can use these data to predict the behavior of bank customers.Then the results can provide banks with more accurate decisions guidance.Data mining techniques can find the information behind the data to further help banks to manage customer relationships better.Then the competitiveness of banks will be enhanced.This paper discusses the application of the data mining technology in customer relationship management of banks,particularly the applications in customer segmentation.These applications in the customer relationship management of banks are significant.In this paper,the data mining method was used to study the bank customer segmentation problem.Firstly,the indices of the customer segmentation were determined.Based on RFM model,the recency(R)?the frequency(F)and the amount(M)were determined.Secondly,customer clustering method was used to cluster customers into four categories.Then the characteristics of each type of customers were analyzed to offer different marketing proposals for banks.Finally,the quantile regression method was used to study the influence factors of total customer deposits.Then the results were analyzed to draw some conclusion.RFM model and clustering method were used to study customers segmentation.Then the quantile regression method was used to study the influence factors of total customer deposits.The above study provided guidance for banks to help them make better marketing tactics.