This project focuses on predicting customer churn using machine learning techniques. It involves the development of a predictive model trained on a dataset containing various customer attributes and their churn status. The goal is to identify patterns and factors contributing to customer churn, enabling businesses to take proactive measures to retain customers.
- Dataset: Utilizes a dataset containing 7044 entries and 21 features.
- Predictive Model: Implements machine learning algorithms such as logistic regression for churn prediction.
- User Interface: Includes a Flask-based web application with options for manual data entry and CSV file upload.
- Accuracy Metrics: Evaluates model performance using accuracy, precision, recall, and F1-score.
- Insights and Recommendations: Provides actionable insights and recommendations based on churn predictions.
To run the project locally, follow these steps:
- Clone the repository:
git clone <repository_url> - Navigate to the project directory:
cd Customer_Churn_Prediction - Install dependencies:
pip install -r requirements.txt - Run the Flask application:
python app.py
- Access the web application by visiting the provided URL.
- Choose the prediction method: manual entry or CSV file upload.
- Fill in the required fields or upload a CSV file containing customer data.
- Click the "Predict" button to generate churn predictions.
- View the results and recommendations provided by the application.
- Flask: Web framework for developing the user interface.
- Pandas: Data manipulation and analysis library.
- NumPy: Numerical computing library.
- Scikit-learn: Machine learning toolkit for model training and evaluation.
This project is licensed under the MIT License.