Feature intersection for agent-based customer churn prediction

Abstract

Purpose Telecommunication has a decisive role in the development of technology in the current era. The number of mobile users with multiple SIM cards is increasing every second. Hence, telecommunication is a significant area in which big data technologies are needed. Competition among the telecommunication companies is high due to customer churn. Customer retention in telecom companies is one of the major problems. The paper aims to discuss this issue. Design/methodology/approach The authors recommend an Intersection-Randomized Algorithm (IRA) using MapReduce functions to avoid data duplication in the mobile user call data of telecommunication service providers. The authors use the agent-based model (ABM) to predict the complex mobile user behaviour to prevent customer churn with a particular telecommunication service provider. Findings The agent-based model increases the prediction accuracy due to the dynamic nature of agents. ABM suggests rules based on mobile user variable features using multiple agents. Research limitations/implications The authors have not considered the microscopic behaviour of the customer churn based on complex user behaviour. Practical implications This paper shows the effectiveness of the IRA along with the agent-based model to predict the mobile user churn behaviour. The advantage of this proposed model is as follows: the user churn prediction system is straightforward, cost-effective, flexible and distributed with good business profit. Originality/value This paper shows the customer churn prediction of complex human behaviour in an effective and flexible manner in a distributed environment using Intersection-Randomized MapReduce Algorithm using agent-based model.

A Stacking-Based Data Mining Solution to Customer Churn Prediction

“…In their proposed method, Pearson product-moment correlation coefficients were utilized in data preprocessing to extract effective features whereas, the k-NN technique (2≤k≤20) was employed to develop and evaluate many models to reduce effect of the noise on the classification Finally, the result showed that the K Nearest Neighbor (k-NN) algorithm performs well compared to the others with the accuracy for training is 80.45% and testing 97.78%. Moreover, in another study of Telecommunication Company,Sandhya et al, (2019) addressed the customer churn problem by recommending an Intersection-Randomized Algorithm (IRA) using Map Reduce functions to avoid data duplication in the mobile user call data. In addition, they also used the agent-based model (ABM) to predict the complex mobile user behaviour to prevent customer churn with a particular telecommunication service provider.…”