CHURN_PREDICTION
This project focuses on predicting customer churn using an Artificial Neural Network (ANN) model. The model was trained to analyze various customer attributes and predict whether a customer is likely to churn. The key features used in this prediction include customer demographics, account details, and activity data.
Technologies Used:
Deep Learning (ANN): The prediction model is based on an Artificial Neural Network (ANN) built using TensorFlow and Keras. Data Processing: Pandas and scikit-learn were used for data manipulation, scaling, encoding categorical variables, and preparing features. Deployment: The model is deployed using Streamlit, an open-source app framework, to create an interactive web application. GitHub: The entire project, including the model, data processing pipeline, and deployment code, is hosted on GitHub for accessibility.
Key Features:
The application allows users to input customer details such as geography, gender, age, balance, credit score, and other factors. After the inputs, the app predicts the likelihood of a customer churning based on the trained model and displays the churn probability. A user-friendly interface is provided via Streamlit, making it easy to interact with the model.