Skip to content

Latest commit

 

History

History
154 lines (102 loc) · 4.18 KB

README.md

File metadata and controls

154 lines (102 loc) · 4.18 KB

Churn Prediction

License Python Flask

Table of Contents

Introduction

Customer churn is when customers stop using a company's services. Predicting churn helps businesses retain customers by identifying at-risk individuals and addressing their concerns.

Project Overview

The Churn Prediction project utilizes machine learning to forecast customer churn based on historical data. It includes data preprocessing, exploratory analysis, feature engineering, model training, and deployment through a Flask web application.

Features

  • Data Cleaning: Handles missing values and encodes categorical variables.
  • Exploratory Data Analysis: Visualizes data distributions and correlations.
  • Model Training: Implements Decision Tree, Random Forest, and ANN models.
  • Deployment: Provides a Flask web app for real-time predictions.

Technologies

  • Language: Python 3.8+
  • Libraries: pandas, numpy, matplotlib, seaborn, scikit-learn, torch, Flask, pickle

Contributors ✨

Thanks to these amazing people for contributing to this repository:

Prabal Patra
Prabal Patra
 Nazim Saifi
Nazim Saifi
 Muhammad Bilal
Muhammad Bilal

Installation

Prerequisites

  • Python 3.8+
  • pip

Steps

  1. Clone the Repository:

    git clone https://github.com/yourusername/Churn_Prediction.git
cd Churn_Prediction

  2. Create and Activate Virtual Environment:

    python -m venv venv
# Windows
venv\Scripts\activate
# macOS/Linux
source venv/bin/activate

  3. Install Dependencies:

    pip install -r requirements.txt

  4. Prepare Dataset:

    Place train.csv and test.csv in the dataset/ folder.

  5. Train Models (Optional):

    Run the notebook in notebooks/Churn_Prediction.ipynb to train and save models.

Usage

Running the Flask App

  1. Navigate to App Directory:

    cd app

  2. Ensure Model is Present:

    Verify models/random_forest_model.pkl exists.

  3. Start the App:

    python app.py

  4. Access the Application:

    Open http://127.0.0.1:5000/ in your browser.

Using the API

Send a POST request to http://127.0.0.1:5000/predict with the required data to receive churn predictions.

Contributing

Contributions are welcome! Follow these steps:

  1. Fork the Repository

  2. Clone Your Fork:

    git clone https://github.com/yourusername/Churn_Prediction.git
cd Churn_Prediction

  3. Create a Branch:

    git checkout -b feature/YourFeature

  4. Commit Changes:

    git commit -m "Description of your feature"

  5. Push and Create Pull Request:

    git push origin feature/YourFeature

License

This project is licensed under the MIT License.