ishamel101/ExpressoChurn-Prediction-Challenge-

The project focuses on predicting churn probability for Expresso, an African telecommunications services company operating in Mauritania and Senegal. # Predicting Churn Probability in African Telecommunications Market: A Streamlit App ## Overview This repository contains the code and resources for a Streamlit web application that predicts churn probability in the African telecommunications market, focusing on Expresso, a leading telecom company operating in Mauritania and Senegal. The app utilizes machine learning techniques to analyze Expresso's customer data and predict the likelihood of churn. ## Dataset The dataset used in this project is sourced from the Expresso Churn Prediction Challenge hosted by the Zindi platform. It comprises information on over 2.5 million Expresso clients, including more than 15 behavioral variables. ## Key Features - **Streamlit Web App:** Interactive web application for predicting churn probability. - **Data Exploration and Preprocessing:** Exploratory data analysis is performed to understand the dataset's structure, features, and distributions. Preprocessing steps such as handling missing values, encoding categorical variables, and feature engineering are conducted to prepare the data for modeling. - **Model Development:** Various machine learning algorithms such as logistic regression, decision trees, random forests, gradient boosting, and neural networks are implemented to build predictive models. Hyperparameter tuning and model evaluation techniques are employed to select the best-performing model. - **Deployment:** The final model is deployed as a Streamlit web app, allowing users to input customer data and receive churn probability predictions in real-time. ## App link: epfjdnrpnobvjhkagzbftx.stre… ##### This project done by: *ISMAIL AIT ALI MHAMED* ##### GITHUB: ishamel101