●5 reads●MIT License
Stock Predictor | AutoReg Model |Streamlit
Table of contents
📊 SP500Forecaster
Predicting S&P 500 Stocks with ML
SP500Forecaster is a machine learning-powered stock price prediction app specifically designed for S&P 500 companies. Built with Python and Streamlit, it leverages historical stock data to forecast future trends and empower investors with data-driven insights.
🧬 Project Structure
SP500Forecaster ├── assets/ │ ├── data/ │ │ └── sp500_tickers.csv │ └── gifs/ │ └── sp500forecaster.gif ├── streamlit_app/ │ ├── modules/ │ │ └── helper.py │ ├── pages/ │ │ └── 01_📈_StockPredictor.py │ └── 00_ℹ️_Info.py ├── LICENSE ├── README.md └── requirements.txt
🛠️ How It's Built
SP500Forecaster is built with the following core frameworks and tools:
- Streamlit - To create an intuitive web interface
- Yahoo Finance API (YFinance) - To fetch up-to-date financial data
- Statsmodels - To implement the AutoReg time-series forecasting model
- Plotly - To generate dynamic and interactive financial charts
- Pandas - To manipulate and process financial datasets
🧑💻 How It Works
- The user selects a stock ticker from the S&P 500 list.
- Historical stock data is retrieved using the Yahoo Finance API.
- The AutoReg (Auto Regressive) model is trained on two years of historical data.
- The model generates forecasts for the next 5–180 days.
- Results are displayed with interactive charts and tables.
✨ Key Features
- Real-time S&P 500 stock data - Access accurate and up-to-date information.
- Interactive charts - View historical trends and future predictions visually.
- Custom prediction ranges - Forecast stock prices for 5 to 180 days.
- Downloadable CSV - Save prediction results for further analysis.
- User-friendly interface - Accessible for novice and experienced users alike.
🚀 Getting Started
Local Installation
- Clone the repository:
git clone https://github.com/user/SP500Forecaster.git
Hint: Replace user with josericodata in the URL above. I am deliberately asking you to pause here so you can support my work. If you appreciate it, please consider giving the repository a star or forking it. Your support means a lot—thank you! 😊
- Navigate to the repository directory:
cd SP500Forecaster
- Create a virtual environment:
python3 -m venv venvStreamlit
- Activate the virtual environment:
source venvStreamlit/bin/activate
- Install requirements:
pip install -r requirements.txt
- Navigate to the app directory:
cd streamlit_app
- Run the app:
streamlit run 00_ℹ️_Info.py
The app will be live at http://localhost:8501
🎬 Demo
Stock Predictor Page:
▶️ Watch the YouTube Tutorial
Click the image above or here to watch the video on YouTube.
🔮 Future Enhancements
Planned improvements and new features include:
- Integration of advanced ML models (e.g., LSTM, Prophet) for better prediction accuracy.
- Multi-stock analysis to compare performance across different stocks.
- Sector-based insights to understand trends within specific industries.
- User accounts and history tracking for tailored predictions and personalized experiences.
🔧 Environment Setup
The SP500Forecaster app is built and tested using the following software environment:
- Operating System: Ubuntu 22.04.5 LTS (Jammy)
- Python Version: Python 3.10.12
Ensure your environment matches or exceeds these versions for optimal performance.
📋 Important Notes
- Data Requirements: Stocks with less than two years of historical data will not be processed by the model.
- Using the Stock Predictor:
- Select a stock ticker from the dropdown menu.
- Choose the desired prediction range using the slider.
- Click the Run Prediction button to generate results.
🤝 Open Pull Requests
If you find any bug, feel free to contact me by opening a pull request on GitHub or via email at maninastre@gmail.com.
⚠️ Disclaimer
This app is designed to demonstrate my skills in data modeling and analytics, showcasing how data-driven insights can assist in building my portfolio as a data analyst. It is not intended to provide financial advice or investment guidance. The predictions are for illustrative purposes only and should not be relied upon for making financial decisions.