Differences between Sharpe in Precheck and Sharpe in strategy.ipynb

[multi_byte.wildebeest]

Hi, I am designing a deep learning model, and I want to get the estimated Sharpe.

I had different results between running Precheck.ipynb and strategy.ipynb.

I have tried like get_sharpe(data, weights) in strategy.ipynb as guided and got the same results as using backtest_ml.

So, what sharpe will be more close to the IS score (>= 1.0 for submission)

Thank you.

[support]

@multi_byte-wildebeest The Sharpe ratio on past data should be the same, what is the difference? Are you completely sure that no forward-looking is going on?

[multi_byte.wildebeest]

@support yes, I just use qnt.backtest_ml, which as I know helps avoid forward looking.

You can check out my model and see : Sharpe in strategy, precheck, and IS are different although no forward looking.

Id :
dlsdcexp_4

16765536

Thanks,

[support]

@multi_byte-wildebeest Hi, please check:

https://quantiacs.com/community/topic/560/warning-some-dates-are-missed-in-the-portfolio_history

[multi_byte.wildebeest]

@support Thank you !