Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Look into weighted replay stats by date #285

Open
dtracers opened this issue May 29, 2019 · 1 comment
Open

Look into weighted replay stats by date #285

dtracers opened this issue May 29, 2019 · 1 comment

Comments

@dtracers
Copy link
Member

For player stats we should weight them by how old they are. Player skills Change dramatically over time even within days if they make a big change.
Newer replays should be weighted more heavily in addition to any cutoff.

@twobackfromtheend
Copy link
Member

While good in theory, I highly doubt people play enough for us to have enough games for "new replays" to estimate stats well.

If we were to do this, I'd strongly suggest first looking at the stat distributions, seeing how many replays are needed for a good estimate of the means, and seeing if that threshold is met by whatever weighting we choose to use.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants