Target Cyrus - New Primary Target

Announcements
24

@master_key The Diagnostics are still based on the nomi target and simple corr at this moment?

25

@liborty Improving your corr20v2 may be as simple as retraining on the new target. As shown in the original post, retrained models should have similar corr and better Sharpe under the new scoring. Have you tried that?

26

Existing models were not trained to be good at the new Cyrus target so it is expected scores on the new target would be lower. After retraining scores should be much more similar, but with less draw-down risk!

27

They were correct initially actually so still valid

1 Like
28

I’m just thinking won’t this make things confusing for historic content? References on the forum/discord to CORR20 pre CORR20V2 are going to be talking about a different metric, and it won’t be obvious unless you know that the meaning of CORR20 changed. Also this is going to make our code confusing too, as we’re going to have to remember that our code referencing CORR20 pre this change were actually referencing CORR20V1. Wouldn’t it be clearer to keep referring to it as CORR20V2?

Also is this going to be the case for the API too, e.g. CORR20V2 will disappear from the API and will be queried via CORR20 instead? If so couldn’t that silently break people’s code?

2 Likes
29

Hi,
I thought that from May 13th the training dataset would use Cyrus as the column “target” but it seems, at least for the int8 version that I have just downloaded, that Nomi is still the main target (Corr 1 with “target” column).
Did I miss anything? Isn’t Cyrus being used from this round?

image

Thanks

1 Like
30

You’re right - this didn’t get changed on time but this round is scoring on Cyrus. Sorry for the confusion.

31

Are both TC and CORR20 payouts based on target_cyrus_v4_20 beginning with round 484?

32

TC doesn’t have a target.