Skip to content

Repository files navigation

NSE-Neuron Logo

Deep Learning powered Stock Price Forecasting for NSE India

Python TensorFlow FastAPI React GitHub stars


UI Demo


What it does

NSE-Neuron fetches historical data for any NSE-listed stock and uses deep learning to forecast the next 5 trading days — giving you predicted High, Low, Close prices along with BUY / HOLD / SELL signals and market regime detection.

Available as a web UI (one-click launch) and a command-line tool.


Screenshots


Highlights

  • 🤖 4 models — LSTM · BiLSTM · GRU · CNN-LSTM, each with its own signal classifier
  • 📊 Run All mode — trains all 4 models at once and ranks them by RMSE
  • 🔍 Regime detection — identifies BULL / BEAR / SIDEWAYS market and recommends the best model
  • 🕯️ Candlestick patterns — detects active patterns and cross-references them with the regime
  • 📈 Interactive chart — zoomable OHLC chart with forecast overlay and signal markers

Quick Start

# 1. Clone
git clone https://github.com/NayakwadiS/NSE-Neuron.git
cd NSE-Neuron

# 2. Python environment
python -m venv .venv
.venv\Scripts\activate          # Windows
source .venv/bin/activate       # macOS / Linux
pip install -r requirements.txt

# 3. Frontend
cd src/frontend && npm install && cd ../..

Launch Web UI

start.bat          # Command Prompt

Open http://localhost:5173 in your browser.

Or use the CLI

python main.py

License

Licensed under the terms of the LICENSE file.

Disclaimer — For educational and research purposes only. Not financial advice. The authors are not responsible for any investment decisions made based on this tool.


🚀 Check out NSE-AI — an AI-Powered NSE Stock Analysis & reasoning engine built on top of this project.

Made with ❤️ for the Indian Stock Market

About

🧠 AI based Indian stock market prediction with deep learning framework. Predicts 5-day OHLC prices + Buy/Hold/Sell Signals with candlestick visualization.

Topics

Resources

Contributing

Stars

16 stars

Watchers

1 watching

Forks

Releases

Sponsor this project

Contributors

Languages