An Approach to Churn Prediction for Cloud Services Recommendation and User Retention

The digital world is very dynamic. ability to timely identify possible vendor migration trends or customer loss risks important in cloud-based services. This work describes a churn risk prediction system and how it can be applied guide cloud service providers for recommending adjustments the subscription level, both promote rational resource consumption avoid CSP loss. A training dataset was built from real data about customer, subscribed its usage history, used supervised machine-learning approach prediction. Classification models were evaluated based on multilayer neural networks, AdaBoost random forest algorithms. From experiments with our dataset, best results obtained forest-based model, 64 estimators, having 0.988 accuracy 0.997 AUC value.