User Profiling and Behavior Evaluation Based on Improved Logistics Algorithm

Abstract

With the development of big data technologies and algorithms, the in-depth analysis of user data collected by user call center becomes possible. Traditional customer call center has notable shortcomings in the intelligent assessment and analysis of internal and external factors affecting customer behavior. If the impact degree and duration of user complaints cannot be accurately predicted, it will seriously hinder employee performance evaluation and enterprise development. In this paper, we proposed a novel framework to do the user profiling and predicted the user's complain probability. The experiments conducted on the 95598 call center users in Guangxi in the first quarter of 2018 show that the developed model has better distinguishing ability and accuracy than the traditional Logistics model in evaluating user behaviors. It can effectively predict the behavior of power users in advance, which is beneficial for power companies to avoid the risk of complaints, thus continuously and effectively improve user experiences, and has substantial economic and social benefits.