0
$\begingroup$

I am currently trying to check the Feature Autocorrelation for a Trend Strategy. I am using XGBoost for that purpose. In addition I work with SHAP.

In the first run I realized that without Standardization of the Mean Return and Volatility SHAP will give those two Features a importance that high, so that SHAP isn't able to check the Autocorrelation Features. Now I standardized the Mean return by subtracting the mean of the portfolio to every cell. I standardized the Vola by diving the previous calculated value by the Vola of the Portfolio and multipliying by 0.015.

I am checking the Autocorrelation by the Risk-Adjusted return (Sharpe Ratio) my question is now: Do I need to use the Standardized Values for Sharpe Ratio or the NOT standardized Values?

$\endgroup$
2
  • $\begingroup$ Just to be clear - could you list exactly the features you are using (that are relevant to this question), and the transformations/standardizations you apply? $\endgroup$ Jun 18, 2021 at 14:03
  • $\begingroup$ The standardization is like mentioned above: I use the pre standardized returns and subtract the average return (for the whole timeframe) for each column. In the second step I divide the new value by the standard deviation (for the whole timeframe) and multiply it by 0.015 to get the annualized standard deviation by that. The other Features that I am using are Lag-1 Autocorrelations of my investments strategy over different frequenzies. $\endgroup$ Jun 18, 2021 at 15:04

1 Answer 1

0
$\begingroup$

It is not possible. For this solution you need to use the standardized data.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

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