jo-cho / trading-rules-using-machine-learning

A financial trading method using machine learning.

Trading rules using machine learning

This is my financial trading using ML.

• Example
• Project

Momentum prediction and enhancing the strategy with machine learning

1. Financial Data and Bars

   • Form time/dollar bars with tick data

2. Get Buy/Sell Signals

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

3. Trading Rules

   • Set enter rules with trading signals from classifiers
   • Set exit rules with profit-taking, stop-loss rate, and maximum holding period
   • (For enhancing the strategy) Label the binary outcome (Profit or Loss)

4. Strategy-Enhancing ML Model

• Get Features (X)

  • Market data & Technical analysis
  • Microstructure features
  • Macroeconomic variables
  • Fundamentals
  • news/public sentiments (in progress)

• Feature Engineering

  • Feature selection, dimension reduction

• Machine Learning Model Optmization

  • Cross-validation (time-series cv / Purged k-fold)
  • Hyperparameter tuning
  • AutoML with autogluon (or simply using ensemble methods such as Random forest, LightGBM, or XGBoost)
  • Metrics (accuracy, f1 score, roc-auc)

• Outcome

  • Bet confidence (probability to accept a single trading signal)

4. Trading Decision

   • Decide to bet or pass for each trading signal from the momentum strategy. The ML model above will help you.
   • Bet sizing with some advanced models (in progress)

5. Backtesting

   • Cumulative returns, Sharpe ratio, max drawdown, win ratio

References:

• Advances in Financial Machine Learning, Lopez de Prado (2018)

Flowchart

trading-rules-using-machine-learning's Issues

Error when reading kospi

hello, very interesting work you've done. I have a problem when runing your code. When runing the following code:
import FinanceDataReader as fdr
import datetime as dt
start_date = dt.datetime(2011,1,1)
end_date = dt.datetime(2021,1,1)

kospi = fdr.DataReader('KS11',start_date,end_date)

I get the following error message, any solution?
Traceback (most recent call last):
File "e:/myquant/Adv_Fin_ML/trading-rules-using-machine-learning-main/test.py", line 7, in
kospi = fdr.DataReader('KS11',start_date,end_date)
File "e:\myquant\venv_quant389\lib\site-packages\FinanceDataReader\data.py", line 41, in DataReader
df = reader(symbol, start, end, exchange, data_source).read()
File "e:\myquant\venv_quant389\lib\site-packages\FinanceDataReader\investing\data.py", line 62, in read
curr_id = self._get_currid_investing(self.symbol, self.exchange, self.data_source)
File "e:\myquant\venv_quant389\lib\site-packages\FinanceDataReader\investing\data.py", line 30, in get_currid_investing
jo = json.loads(r.text)
File "E:\ProgramFiles\Python\Python38\lib\json_init.py", line 357, in loads
return _default_decoder.decode(s)
File "E:\ProgramFiles\Python\Python38\lib\json\decoder.py", line 337, in decode
obj, end = self.raw_decode(s, idx=_w(s, 0).end())
File "E:\ProgramFiles\Python\Python38\lib\json\decoder.py", line 355, in raw_decode
raise JSONDecodeError("Expecting value", s, err.value) from None
json.decoder.JSONDecodeError: Expecting value: line 1 column 1 (char 0)

images