In this project, we will
- Explore and estimate an IRL-based model of market returns that is based on IRL of a market-optimal portfolio
- Investigate the role and impact of choices of different signals on model estimation and trading strategies
- Compare simple IRL-based and UL-based trading strategies
by implementing the model of Halperin and Feldshteyn (2012) for DJIA and SP500
Data and Jupyter notebook files are included so one can reproduce the results and make future enhancement.
dja_cap.csv - containes DJIA stock prices
spx_holdings_and_spx_closeprice.csv - contains SP500 stock prices
SSRN-id3174498.pdf - the paper that describes the IRL model
IRL_market_model-paper-multiple_stocks-with_next_day return_and_SP500.ipynb - Python notebook
tensorflow_optimization_examples.ipynb - an example of using Tensorflow for minimizing the Maximum Likelihood function