Expresso an African telecommunications services company that provides telecommunication services in two African markets: Mauritania and Senegal required a predictive machine learning model to predict the likelihood of each Expresso customer “churning,” i.e. becoming inactive and not making any transactions for 90 days. This solution will help Expresso to better serve their customers by understanding which customers are at risk of leaving.
My approach involved exploratory data analysis and feature engineering to understand the factors driving telecoms churn afterwards modelling using a gradient boosting decision tree CatBoost model.