Quant Pulse 🚀📈

Catch market spikes before they happen, powered by AI!

Quant Pulse is a real time AI system designed to predict short term market volatility and micro movements in stocks and crypto it's built for traders, quants, and ai enthusiasts who want to catch market spikes before they happen

---

⚡ features

• real time market ddata ingestion from stocks & crypto

• advanced feature engineering:

  • technical indicators (EMA, RSI, bollinger bands, VWAP)

  • order book features (bid-ask imbalance, liquidity)

  • rolling volatility & momentum

• predicitve models: LSTM, transformer, XGBoost / lightGBM ensemble

• backtesting module to simulate strategies on historical data

• live dashboard (streamlit / dash) to visualize predictions and alerts

---

📊 architecture

live market data --> preprocessing --> feature engineering --> predictive model --> alet / dashboard

diagram

    ┌───────────────────┐
    │ live Market Data  │
    └────────┬──────────┘
             │
             ▼
    ┌───────────────────┐
    │ preprocessing     │
    └────────┬──────────┘
             │
             ▼
    ┌───────────────────┐
    │ feature Engineering│
    └────────┬──────────┘
             │
             ▼
    ┌───────────────────┐
    │ predictive Model  │
    └────────┬──────────┘
             │
    ┌────────┴──────────┐
    │ alert / dashboard │
    └───────────────────┘

---

💻 tech stack

• data ingestion: yfinance, ccxt, alpha vantage

• processing & features: pandas, numpy, ta-lib

• modeling: pyTorch, TensorFlow, XGBoost, LightGBM

• visualization: plotly, dash, streamlit

• backtesting: backtrader, zipline-reloaded

---

exemple output

---

📂 folder structure

• data/ # raw + processed datasets

• src/

  • data_loader.py # fetch + preprocess data

  • features.py # feature engineering

  • model.py # training & interference scripts

  • backtest.py # backtesting module

  • dashboard.py # streamlit or Dash dashboard

• notebooks/ # exploratory data analysis

• requirements.txt # libraries needed for the project

• README.md # explanation of this project

• .gitignore

---

🚀 getting started

1. clone this repo

git clone https://github.com/Youcef3939/QuantPulse.git

cd QuantPulse

2. create a virtual environment

python -m venv venv

source venv/bin/activate # Linux / Mac

venv\Scripts\activate # Windows

3. install requirements

pip install -r requirements.txt

4. run the dashboard

streamlit run dashboard/app.py

5. there's also a demo.ipynb in noteboos/ check it out!!

---

📈 contributing

contributions, ideas, and feedback are welcome!

open an issue or submit a PR and let's make Quant Pulse even better together <3

---

⚠ DISCLAIMER

THIS PROJECT IS FOR EDUCATIONAL PURPOSES ONLY

DO NOT AND I MEAN DO NOT USE THIS FOR LIVE TRADING WITHOUT PROPER TESTING AND RISK MANAGMENT!!!

---

if you find this project useful or fun, feel free to give a ⭐ and fork it!