News Over-Fitting Avoidance

So recently I've been studying the whole over-fitting problem, and there is a small thing that I think prevents SQ X from being trully Robust optimization software, and that is the overlooked area of news Avoidance.



Currently there isn't a feature during backtesting that helps prevent Over-Optinization to news events.


Here's a guy that explains this topic much better than me, and I think SQ team should implement his formula to the optimizer: https://youtu.be/0ZJ1_DLFdbM

Attachments
No attachments
  • Votes +1
  • Project StrategyQuant X
  • Type Feature
  • Status New
  • Priority Normal

History

YR
#1

yevg555

22.12.2020 20:37

Task created

JA
#2

johancdb

15.02.2021 20:14
Voted for this task.

Votes: +1

Drop files to upload

or

choose files

Max size: 5MB

Not allowed: exe, msi, application, reg, php, js, htaccess, htpasswd, gitignore

...
Wait please