Customer Churn Prediction

This project focuses on building a predictive model to identify potential customer churn in a telecommunications company. The process includes data cleaning, exploratory data analysis (EDA), feature engineering, and machine learning model development using Logistic Regression. To enhance usability, an interactive Streamlit web app was built, enabling real-time churn prediction based on user inputs.

Python (pandas, numpy, matplotlib, seaborn, scikit-learn, joblib)
Streamlit (for interactive web app)
Google Colab (for model development)
Git & GitHub (for version control and deployment)
VS Code (local development and Streamlit testing)

Tools & Technologies Used

Key Highlights

Performed end-to-end data preprocessing and feature encoding
Built and evaluated churn prediction model with 80%+ accuracy
Created a dynamic Streamlit app for live churn predictions
Deployed on Streamlit Cloud for public access

Links

Github: Customer-Churn-Prediction

Live App: customer-churn-prediction-app