Abstarct: Abstract Today, companies and organizations are aware of the fact that customer retention leads to greater profitability, and on the other hand, increasing competition causes the rate of churn customer to increase. Therefore, studying the features influencing the tendency of customers to turn or not to turn, is important for both researchers and businesses. In this research, a hybrid model baxsed on data mining approach is presented to analyze the features of churn customer. In the first step, Bayezian Network aloritm has been used to identify the features with higher importance and remove redundant items. In the second step, C5.0 Decision Tree were used to classify the customers into two groups, turning customers and non-turning customers, which are data mining techniques and can help in forecasting. Finally, the proposed model has been implemented in the chain store industry as a case study. The results indicate the optimal efficiency of the proposed analysis method. Also, the results show that three features of gender, education level, average monthly income level from the set of demographic characteristics and four factors of number of purchases per month, share of online shopping, how to get to know the store,number purchases in the month related to customer transaction records are among the most important effective factors. They are known for turning customers around. …………….