A minimal, production-ready scaffold for a deep-learning trading bot that runs in:
- Paper mode (local JSON ledger; no real orders)
- Live mode via E*TRADE API (OAuth 1.0a; sandbox or production)
It supports multiple symbols, basic risk controls, and a one-flag switch between paper and real trading.
⚠️ Educational use only. Not investment advice. Always validate behavior in paper and sandbox before using real money.
bot.py: trading loop, risk management, brokerstrain_model.py: trains thePriceLSTMused by the botmodels/model.pt: saved PyTorch weights (produced bytrain_model.py)paper_ledger.json: created automatically in paper mode
python -m venv .venv
source .venv/bin/activate # Windows: .venv\Scripts\activate
pip install --upgrade pip
pip install torch numpy pandas scikit-learn requests yfinance