0
$\begingroup$

For a given asset, I have simulations of the price and implied volatility for T periods in N scenarios. Furthermore, assuming that I know the value of the risk-free asset (and the dividend yield), I can calculate the price of the calls and puts options on different maturities and strikes (at least with Black-Scholes). I would like to build a program that autonomously selects a winning strategy on average in the N scenarios - combining the underlying, call and put so that -the expected profit in the different scenarios is maximized. The aim is to have a rule of this type: 'when the volatility is under 15% and the stock had fallen in the last 3 days, buy the put X (maturity, moneyness) and the underlying'. Could you suggest any technique?

$\endgroup$
0
$\begingroup$

You have plenty of potential solutions, the easiest one is decision tree models like Random Forest.

Then, you can try more complex models based on LSTM or Reinforcement Learning.

Here are 2 code examples using RF:

https://python.plainenglish.io/how-to-predict-stock-prices-change-with-random-forest-in-python-f707e101d5c4

https://tcoil.info/predict-stock-price-trend-with-machine-learning-random-forest-scikit-python/

Here are 2 code examples using RL:

https://www.analyticsvidhya.com/blog/2020/10/reinforcement-learning-stock-price-prediction/

https://towardsdatascience.com/deep-reinforcement-learning-for-automated-stock-trading-f1dad0126a02

$\endgroup$
2
  • $\begingroup$ Thank you very much! $\endgroup$ Jul 27 at 14:06
  • $\begingroup$ You're welcome Alessio. If the answer was usefull, do not hesitate to upvote it :) $\endgroup$ Jul 27 at 14:10

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.