Research On The Early Warning Model Of Customer Churn In Automobile 4S Stores

With the rapid development of China’s real economy,the car industry has become an important industry to support the economic development of our country.Especially in recent years,the popularity of new energy vehicles and the rapid development of ride-hailing have brought new historical opportunities for the automobile industry.Therefore,the classification and research of automobile 4 S store customers is of great significance.This paper analyzes the customer information of automobile4 S stores with the data of 4 S store customers in 2019.This paper uses the traditional RFM model and the improved RFM model to classify the customer data,and compares the classification results.On the one hand,this paper compares the differences between the traditional RFM model and the improved RFM model for the definition of each index.The R、F、M indexes are redefined by proportional method and a new index S is introduced in the improved RFM.The weight of each index is calculated by analytic hierarchy process,and the weighted index is clustered by K-means cluster.On the other hand,the clustering results of the two methods are compared.Through the model comparison,the improved RFM model can well divide customers into 8 categories.The traditional RFM model can only classify customers into 4 categories and the difference between each categories is not significant.Thus it is concluded that the improved RFM model performs better in the effect of customer segmentation in automobile industry.