📈 Real-Time Stock Movement Predictor using SVM + Streamlit

🚀 Try the Live Demo
👉 Live App
🧠 GitHub Repo

📸 Project in Action
UI:

Model Evaluation:

💡 What Does This App Do?

It predicts whether a stock’s next-day movement will be:

📈 UP or 📉 DOWN

You simply:

Choose a stock (AAPL, MSFT, TSLA, etc.)
Click “Predict”
See the next-day prediction powered by an SVM model

🔧 How It Works

✅ Features Used:

Past 3-day returns
Short & Long moving averages
Momentum = short − long
Volatility (rolling std dev)
Ticker encoded as a feature

📊 Model:

SVM classifier trained on 3 years of daily data (from Yahoo Finance)
Achieved ~99% test accuracy 🎯

🛠️ Tech Stack

Component	Tool / Library
Model	Scikit-learn (SVM)
Data Source	yfinance (Yahoo Finance API)
Frontend	Streamlit
Feature Engg	pandas, NumPy
Visualization	seaborn, matplotlib

📁 Project Structure

stock-movement-svm/
├── app.py # Streamlit frontend + logic
├── model.pkl # Trained SVM model
├── scaler.pkl # Feature scaler
├── generate_features.py # Feature generation logic
├── requirements.txt
├── screenshots/
│ ├── screenshot-ui.png
│ └── confusion-matrix.png
└── README.md

🔌 Run Locally

git clone https://github.com/snoorbasha50/stock-movement-svm.git
cd stock-movement-svm
pip install -r requirements.txt
streamlit run app.py

🔍 Future Enhancements

Add more stocks dynamically
Include candlestick chart visualizations
Fine-tune SVM hyperparameters
Try LSTM or deep learning for sequence modeling

📬 Let’s Connect

💼 LinkedIn
🌐 GitHub

Comments

[Samir Tahiri]

💪🏼💪🏼

[Nathan Tarbert]

This is extremely impressive, especially seeing the whole flow from UI to model all lined up