Empowering smarter investment decisions through Machine Learning and Data-Driven Insights.
🧠 Overview
StockVerse is a powerful machine learning–based project designed to analyze and predict stock market trends using both classification and regression models. It processes NIFTY 50 historical data to predict:
📉 Whether the stock price will go UP or DOWN
💰 The next day’s closing price
Built with Streamlit, scikit-learn, and Pandas, it provides an intuitive dashboard for visualization and live prediction.
🚀 Features
✅ Dual Machine Learning Models
Logistic Regression → Predicts movement direction (Up/Down)
Linear Regression → Predicts next-day closing price
✅ Streamlit Dashboard
Real-time prediction from user input
Visualized recent stock trends
✅ Data Engineering Pipeline
Cleans and processes raw NIFTY50 data
Handles missing values and scaling
✅ Modular Structure
Separate scripts for training, prediction, and UI
✅ Open for Contribution
Anyone can fork this repo and enhance the features further
🧩 Tech Stack Component Technology Language Python 3.x Framework Streamlit ML Libraries scikit-learn, Pandas, NumPy, Joblib Data Source NIFTY50 Historical Stock Data Version Control Git & GitHub 🗂️ Project Structure StockVerse/ │ ├── data/ │ ├── engineered_stock_data.csv │ └── engineered_stock_data_sample.csv │ ├── models/ │ ├── logistic_model.pkl │ └── linear_model.pkl │ ├── src/ │ ├── app.py # Streamlit dashboard │ └── model_trainer.py # Model training script │ ├── requirements.txt ├── README.md └── .gitignore
⚙️ Installation and Setup 1️⃣ Clone the Repository git clone https://github.com//StockVerse.git cd StockVerse
2️⃣ Create and Activate Virtual Environment python -m venv venv venv\Scripts\activate # On Windows
source venv/bin/activate # On Mac/Linux
3️⃣ Install Dependencies pip install -r requirements.txt
4️⃣ Train the Models
(If you want to retrain with your dataset)
python src/model_trainer.py
5️⃣ Run the Streamlit App streamlit run src/app.py
💾 Model Files
After training, models are automatically saved to:
models/logistic_model.pkl models/linear_model.pkl
🌐 Deployment
You can deploy this project easily using:
Streamlit Cloud
Render
Hugging Face Spaces
Just make sure your folder structure is preserved and your dataset (or sample dataset) is uploaded inside /data.
🧮 Example Predictions Input Features Logistic Output Linear Output RSI: 48, MA5: 1800, Volatility: 0.5 📈 UP ₹1834.76 RSI: 72, MA5: 420 📉 DOWN ₹409.22 🛠️ Commands Reference Task Command Install dependencies pip install -r requirements.txt Run dashboard streamlit run src/app.py Train models python src/model_trainer.py Push changes git add . && git commit -m "update" && git push origin main 🤝 Contributing
We welcome all contributions! 🎉 You can fork this repository and modify it to give it a better shape — add new models, data sources, or improve visualization.
Steps to contribute:
Fork this repo
Create your feature branch
git checkout -b feature/NewFeature
Commit your changes
git commit -m "Added new feature"
Push to branch and open a Pull Request
git push origin feature/NewFeature
💬 Contact
📧 Developer: [Your Name or GitHub Profile] 🌐 GitHub: https://github.com//StockVerse
📄 License: MIT
⭐ If you like this project, give it a star on GitHub and share it with your community!
Let’s make StockVerse smarter together 🚀