关键词: 知识流动, 热点数据, 成品油销售, 客户流程

Abstract: Aiming at the problems of inaccurate prediction of customer loss and untimely identification of customer loss risk, combined with the changing characteristics of hot data of knowledge flow, an optimization model of retail customer loss of refined oil enterprises is established. According to the purchase behavior characteristics of users, the retail customers of refined oil enterprises are divided, the hot data of retail knowledge flow of refined oil enterprises are collected, different factors affecting customer loss are analyzed, target variables, influence variables and input variables are set, and the monthly loss rate is defined as a metric indicator. The loss of retail customers of refined oil enterprises is determined and predicted by the type of customer loss, The output results of the model are obtained. The case verification results show that the model can obtain more accurate customer churn prediction results, and provide reference for the maintenance of exploration customers of product oil enterprises.

Key words: knowledge flow, hotspot data, refined oil enterprises, customer flowchart