Churn-Predictor-ANN

Visit the web application: Churn Predictor App

Description

Churn Predictor - Web Application: Predict customer churn using an ANN model deployed in a user-friendly Streamlit app. The application leverages standard preprocessing techniques including label encoding, one-hot encoding, and scaling. Users can input customer details to predict churn probability with a dynamic and interactive interface. The model achieves an accuracy of 85%.

Features

• Predict customer churn using an ANN model.
• User-friendly interface built with Streamlit.
• Standard preprocessing techniques: label encoding, one-hot encoding, and scaling.
• Interactive input for customer details.

Video Demo

Check out the video demo below to see the application in action:

streamlit-app-2024-12-20-13-12-24.webm

Technologies Used

• Programming Language: Python
• Libraries: Pandas, NumPy, Seaborn, Matplotlib, Scikit-learn, TensorFlow, Keras, Pickle
• Web Framework: Streamlit
• Deployment: Streamlit

Installation

1. Clone the repository:

   git clone https://github.com/sai-manas/Churn-Predictor-ANN.git

2. Navigate to the project directory:

   cd Churn-Predictor-ANN

3. Install the required dependencies:

   pip install -r requirements.txt

Usage

Running the Streamlit Web Application

1. Navigate to the project directory:

   cd Churn-Predictor-ANN

2. Run the Streamlit app:

   streamlit run app.py

Jupyter Notebooks

Check the notebooks for model training and prediction processes here:

• ANN.ipynb

Deployment on Streamlit

To deploy the application on Streamlit from GitHub:

1. Go to Streamlit.
2. Sign in with your GitHub account.
3. Create a new app and connect it to your GitHub repository.
4. Select the branch and the main file (app.py) to deploy.
5. Click "Deploy" to launch your application.