murithidenisgitobu/Customer-Churn-Prediction-Challenge-For-Azubian

This challenge is for an African telecommunications company that provides customers with airtime and mobile data bundles. The objective of this challenge is to develop a machine learning model to predict the likelihood of each customer “churning,” i.e. becoming inactive and not making any transactions for 90 days. # Project Title Customer Churn Prediction (Telecommunication Company) - Challenge for Azubian ## Project Description This challenge is for an African telecommunications company that provides customers with airtime and mobile data bundles. The objective of this challenge is to develop a machine learning model to predict the likelihood of each customer “churning,” i.e. becoming inactive and not making any transactions for 90 days. | Variable | Description | |------------------|---------------------------------------------------| | user_id | Unique identifier for each client | | REGION | The location of each client | | TENURE | Duration in the network | | MONTANT | Top-up amount | | FREQUENCE_RECH | Number of times the customer refilled | | REVENUE | Monthly income of each client | | ARPU_SEGMENT | Income over 90 days / 3 | | FREQUENCE | Number of times the client has made an income | | DATA_VOLUME | Number of connections | | ON_NET | Inter expresso call | | ORANGE | Call to orange | | TIGO | Call to Tigo | | ZONE1 | Call to zones1 | | ZONE2 | Call to zones2 | | MRG | A client who is going | | REGULARITY | Number of times the client is active for 90 days | | TOP_PACK | The most active packs | | FREQ_TOP_PACK | Number of times the client has activated the top pack packages | | CHURN | Variable to predict - Target | ## API Referenc …