A Novel Algorithm and System of Customer Value Evaluation based on Telecom Operator Big Data

With the increasing market competition, telecom operators need to improve the level of services, ensure the quality of experience, as well as reduce the cost of enterprise. Therefore it is crucial to evaluate the value of telecom customers accurately. The traditional method of telecom customer value assessment is mainly based on ARPU (Average Revenue Per User), which is one-dimensional and cannot evaluate customer value comprehensively. This paper proposes a multidimensional customer value assessment method, including two perspectives, Current value and Potential value to improve the accuracy and comprehensiveness of evaluation. Also, an intelligent method based on swarm intelligence algorithm is presented to calculate the indicator weight for each characteristic field of customer value. The practical results show that the algorithm, which is applied to realistic scenarios of network operation, enables telecom operator to achieve a comprehensive and accurate customer value assessment in many issues such as customer churn warning and accurate recommendation, ultimately increasing the effectiveness and efficiency of decision-making closed loop for telecom operators. At last but not the least, the algorithm and system can benefit other industries to improve their intelligence level of customer service.