Churn Prediction on Huge Sparse Telecom Data Using Metaheuristic

Abstract: Churn prediction in telecom has become a major requirement due to the increase in the number of telecom providers. However due to the hugeness, sparsity and imbalanced nature of the data, churn prediction in telecom has always been a complex task. This paper presents a Metaheuristic based churn prediction technique that performs churn prediction on huge telecom data. Particle Swarm Optimization algorithm is used as the classifier. Experiments were conducted on the Orange dataset. It was observed that PSO algorithm works best on churn data providing effective and faster results.

Keywords: Telecom churn prediction, Data Imbalance, Data Sparsity, Huge Data; PSO