sharavsambuu / trading-rules-using-machine-learning

This is my financial trading system using ML (Random forest & LSTM). Most of the methods are based on 'Advances in Financial Machine Learning' by Lopez de Prado.

Trading rules using machine learning

• This is my financial trading system using ML.

• See Notebook

• The other example using daily stocks: Project

Momentum strategy with machine learning

1. Financial Data and Bars

   • Form time/dollar bars with tick data

2. Getting Trading Signals

   • Momentum strategy (RSI..)
   • Additional ML regime detector

3. Trading Rules

   • Enter rules with trading signals
   • Exit rules (triple-barrier method)
   • Binary Labeling (Profit or Loss)

4. Strategy Enhancing ML Model

• Get Features (X)

  • Market data & Technical analysis
  • Microstructure features
  • Macroeconomic variables
  • Fundamentals
  • public sentiments with NLP

• Feature Engineering

  • Feature scaling
  • Dimension reduction
  • Feature Analysis with feature importance
  • Feature selection

• Machine Learning Model

  • Cross-validation (time-series cv / Purged k-fold)
  • Hyperparameter tuning
  • AutoML with autogluon and select the best model
  • Results (accuracy, f1 score, roc-auc)

4. Trading
   • Bet Sizing
   • Trading Simulation
5. Results
   • Cumulative returns, Sharpe Ratio, max drawdown

Financial Data and Bars

• ETH/USD 5 min data (2019.1.1 ~ now)
• The trading rule is based on Triple-Barrier Method introduced in Lopez De Prado (2018).

References:

• Advances in Financial Machine Learning, Lopez de Prado (2018)
• ta, https://github.com/bukosabino/ta
• autogluon, https://github.com/awslabs/autogluon

Flowchart