This project predicts whether a customer is likely to stop patronizing a business. Using historical customer data, the model analyzes patterns and behaviors to provide accurate predictions, enabling businesses to take proactive measures to retain customers.
- Telecommunications: Predicts customer churn based on usage patterns and complaints.
- E-Commerce: Identifies at-risk customers based on purchase frequency, reviews, and interactions.
- Banking and Finance: Anticipates churn for services like credit cards or loans.
- Enhanced Customer Retention: Allows targeted retention strategies for at-risk customers.
- Increased Revenue: Prevents revenue loss by reducing churn.
- Improved Customer Relationships: Enables businesses to personalize interventions for better engagement.
This is a Streamlit web application that predicts whether a customer is likely to churn based on various input features such as credit score, geography, age, and more. The app uses a pre-trained machine learning model.
- Intuitive UI for inputting customer details.
- Provides predictions on customer churn status.
- Clean and interactive interface built using Streamlit.
Ensure you have the following installed:
- Python 3.7 or higher
- Streamlit library
- Necessary dependencies listed in
requirements.txt
- Clone the repository:
git clone https://github.com/Onome-Joseph/Customer-Churn-Prediction.git
- Install dependencies:
pip install -r requirements.txt
- Run the Streamlit application:
streamlit run app.py
- Open the app in your browser. The default URL is:
http://localhost:8501
Contributions are welcome! Feel free to fork the repository or report issues.