# Feature Engineering and Feature Importance in Machine Learning for Financial Markets

[Background knowledge for Feature Analysis in Finance](https://github.com/jo-cho/Technical_Analysis_and_Feature_Engineering/blob/main/Feature%20Analysis%20In%20Finance.ipynb)


## Technical Indicators
- I studied over 80 technical indicators.
    - [1. Technical Indicators - Volume.ipynb](https://github.com/jo-cho/Technical_Analysis_and_Feature_Engineering/blob/main/1.%20Technical%20Indicators%20-%20Volume.ipynb)
    - [2. Technical Indicators - Volatility.ipynb](https://github.com/jo-cho/Technical_Analysis_and_Feature_Engineering/blob/main/2.%20Technical%20Indicators%20-%20Volatility.ipynb)
    - [3. Technical Indicators - Trend.ipynb](https://github.com/jo-cho/Technical_Analysis_and_Feature_Engineering/blob/main/3.%20Technical%20Indicators%20-%20Trend.ipynb)
    - [4. Technical Indicators - Momentum.ipynb](https://github.com/jo-cho/Technical_Analysis_and_Feature_Engineering/blob/main/4.%20Technical%20Indicators%20-%20Momentum.ipynb)
    - [5. Using technical indicators in Meta-labeling.ipynb](https://github.com/jo-cho/Technical_Analysis_and_Feature_Engineering/blob/main/5.%20Using%20technical%20indicators%20in%20Meta-labeling.ipynb)

- [Technical Indicators Binary Matrix](https://github.com/jo-cho/Technical_Analysis_and_Feature_Engineering/tree/main/ti_matrix)
    - for input

Old ones
- T.I. Analysis (old version)
    - [TI Analysis](https://github.com/jo-cho/Technical_Indicators_analysis/blob/main/old%20ones/Tech.Indicators%20Analysis.ipynb)
- Is TA better than simple market data?
    - [TI vs. Simple](https://github.com/jo-cho/Technical_Indicators_analysis/blob/main/old%20ones/Tech.Indicators%20vs.%20Simple.ipynb)

## Feature Importance
- Which one is important? with MDI
    - [Correlation with the PC (principle component) of highest MDI](https://github.com/jo-cho/Technical_Indicators_analysis/blob/main/old%20ones/ML%20PCA%20Feature%20Importance.ipynb)

## Feature Engineering (.. in progress)
- Deep Autoencoder
- CNN architecture
- FinEmbedding

## Data
- High Frequency Cryptos Prices
- Daily Stock Prices

## Other example
- [ML trading rule](https://github.com/jo-cho/trading-rules-using-machine-learning)
- [Simple trading strategies using technical indicators](https://github.com/jo-cho/Technical_Ananylsis_Strategies_Cryptocurrency)
- 
# 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)