Nifty 50 Stock Price Prediction 📈

A machine learning model to predict Nifty 50 stock prices with a Mean Absolute Error (MAE) of ₹60.

Overview

This project implements a stock price prediction model for Nifty 50 companies using historical data. The model achieves high accuracy with a Mean Absolute Error of just ₹60, making it a reliable tool for price forecasting.

Features

• Historical stock price data analysis
• Price prediction for Nifty 50 companies
• MAE of ₹60 on test data
• Easy-to-use prediction script
• Comprehensive Jupyter notebook with analysis

Project Structure

nifty50-prediction/
├── main.ipynb
├── requirements.txt
├── .gitignore
└── README.md

Installation

1. Clone the repository

git clone https://github.com/yash373/nifty-price-predictor.git
cd nifty-price-predictor

2. Install required packages

pip install -r requirements.txt

Usage

Using the Jupyter Notebook

1. Open main.ipynb
2. Follow the step-by-step analysis and model development process

Model Performance

• Mean Absolute Error (MAE): ₹60
• Dataset: Historical Nifty 50 stock prices (All time series)
• Training-Testing Split: 75-25
• Validation Strategy: Time-series cross-validation

Dependencies

• Python 3.8+
• Pandas
• NumPy
• Scikit-learn
• Jupyter

Contributing

1. Fork the repository
2. Create a new branch (git checkout -b feature/improvement)
3. Commit your changes (git commit -am 'Add new feature')
4. Push to the branch (git push origin feature/improvement)
5. Create a Pull Request

License

This project is licensed under the MIT License - see the LICENSE file for details.

Acknowledgments

• NSE India for providing historical stock data
• Open-source community for various tools and libraries