backtesting.py
backtesting.py copied to clipboard
Remove flooring on ratios and adding Kelly Criterion
Fixes https://github.com/kernc/backtesting.py/issues/715
- Remove flooring on Sharpe Ratio
- Adding Kelly Criterion
Any other comments?
Any update on this review?
I've actually been meaning to but just didn't come round to trying it out and seeing what happens when positions are indeed sized as Kelly Criterion recommends. Say I run a backtest and get Kelly Criterion=0.5. Say I now repeat the same strategy backtest with trades size=0.5. What does the Kelly Criterion say at the end of this backtest? And if the value is different from before, of what real use is it?
The traditional meaning of Kelly Criterion is indeed the bet size optimisation parameter. However, it also shows the confidence level on a particular strategy, similar to the Sharpe ratio, the higher is generally better.
In a portfolio sense, it tells the user, how much to invest in this particular strategy as part of user's overall portfolio.
Is it possible to merge in?
Sorry to have taken so long. CI was a mess. Thanks for the PR! :cake: