jo-cho / Technical_Analysis_and_Feature_Engineering

Feature Engineering and Feature Importance in Machine Learning for Financial Markets

Feature Engineering and Feature Importance in Machine Learning for Financial Markets

Background knowledge for Feature Analysis in Finance

Technical Indicators

• I studied over 80 technical indicators.

  • 1. Technical Indicators - Volume.ipynb
  • 2. Technical Indicators - Volatility.ipynb
  • 3. Technical Indicators - Trend.ipynb
  • 4. Technical Indicators - Momentum.ipynb
  • 5. Using technical indicators in Meta-labeling.ipynb

• Technical Indicators Binary Matrix

  • for input

Old ones

• T.I. Analysis (old version)
  • TI Analysis
• Is TA better than simple market data?
  • TI vs. Simple

Feature Importance

• Which one is important? with MDI
  • Correlation with the PC (principle component) of highest MDI

Feature Engineering (.. in progress)

• Deep Autoencoder
• CNN architecture
• FinEmbedding

Data

• High Frequency Cryptos Prices
• Daily Stock Prices

Other example

• ML trading rule
• Simple trading strategies using technical indicators

References

• De Prado, M. L. (2018). Advances in financial machine learning. John Wiley & Sons.
  • Chapter 8 Feature Importance
• Dixon, M. F., Halperin, I., & Bilokon, P. (2020). Machine learning in Finance (Vol. 1170). Berlin and Heidelberg: Springer International Publishing.
  • Chapter 5. Interpretability
  • Chapter 8. 6. Autoencoders
• Jansen, S. (2018). Hands-On Machine Learning for Algorithmic Trading: Design and implement investment strategies based on smart algorithms that learn from data using Python. Packt Publishing Ltd.
  • Chapter 4: Financial Feature Engineering
• Python library ta (https://github.com/bukosabino/ta)