Page 1 of 1
Understanding and Pushing the Limits of the Elo Rating Algorithm
Posted: Tue Oct 15, 2019 10:30 am
by Michel
https://arxiv.org/abs/1910.06081
Nothing that wasn't already known unfortunately.
Re: Understanding and Pushing the Limits of the Elo Rating Algorithm
Posted: Tue Oct 15, 2019 4:39 pm
by Daniel Shawul
How did they miss our work
Paired Comparisons with Ties ?
We compared three draw models and found out Davidson fits chess data best -- which they reframed as their own K-elo if I am not mistaken.
Maybe I should alert the authors to our paper and makes them spell out what their unique contribution.
Re: Understanding and Pushing the Limits of the Elo Rating Algorithm
Posted: Tue Oct 15, 2019 7:01 pm
by Robert Pope
Daniel Shawul wrote: ↑Tue Oct 15, 2019 4:39 pm
How did they miss our work
Paired Comparisons with Ties ?
We compared three draw models and found out Davidson fits chess data best -- which they reframed as their own K-elo if I am not mistaken.
Maybe I should alert the authors to our paper and makes them spell out what their unique contribution.
"The requested page could not be found."
Re: Understanding and Pushing the Limits of the Elo Rating Algorithm
Posted: Tue Oct 15, 2019 10:14 pm
by Daniel Shawul
Re: Understanding and Pushing the Limits of the Elo Rating Algorithm
Posted: Wed Oct 16, 2019 9:01 am
by Michel
You should probably contact them so that they can at least refer to your work.
But I think there is essentially nothing in the paper. As you say k-elo seems to Davidson.
The only thing that could be considered slightly original is that they identify the draw model corresponding to the pseudo likelihood approach to the elo model with draws counting as the average of a win and a loss (i.e. the contribution of a draw to the log (pseudo) likelihood is counted as (1/2)log(w(1-w)) where w is a function of the elo difference). But this is a triviality.
Re: Understanding and Pushing the Limits of the Elo Rating Algorithm
Posted: Fri Oct 18, 2019 11:29 pm
by towforce
Just my opinion, but it seems to me that:
1. optimal chess is a drawn game
2. therefore, at a certain level of skill, all games will be drawn
3. therefore, any rating system that doesn't allow for this is fundamentally flawed
Re: Understanding and Pushing the Limits of the Elo Rating Algorithm
Posted: Sat Oct 19, 2019 2:48 pm
by Fulvio
tl;dr
Based on the ELO difference, the current algorithm gives the following probability of winning:
+0 --> 50%
+100 --> 64%
+200 --> 76%
+300 --> 85%
+400 --> 91%
What are values of the improved algorithm?
Re: Understanding and Pushing the Limits of the Elo Rating Algorithm
Posted: Mon Oct 21, 2019 8:41 pm
by Dann Corbit
A while ago, Kaggle had a contest for improved game outcome prediction algorithms.
Uri did pretty well in the contest, if I remember correctly.