A large telecom provider was struggling with customer churn in a saturated and competitive market. They were working on predicting churn customers but didn’t have enough time to develop and carry out successful churn management strategies.
The model developed for this work used machine learning techniques on a big data platform and built a new way of predicting potential customer churn. One of the main enhancements was to use customer social network data in the prediction model by extracting Social Network Analysis (SNA) features. The use of SNA enhanced the performance of the model by 11%. In addition, the model proactively recommends personalized retention offers. AI predicts what customers want and gives them the offer when they are most at risk for leaving the company.