Computer Chess Club Archives


Search

Terms

Messages

Subject: Re: "Accuracy" of SSDF list

Author: Chris Carson

Date: 08:21:33 03/08/02

Go up one level in this thread


On March 08, 2002 at 08:07:24, Mike Hood wrote:

>As has already been discussed in other threads, ELO ratings only give the
>relative rankings of competitors in a limited pool, although by extending the
>pool to encompass the whole world the ratings can be considered absolute.
>
>The SSDF rating lists can only be taken seriuously if the pool of computer
>programs is periodically calibrated by taking into account games between
>computers and humans.
>
>To what extent is this done?
>
>Are only games between grandmasters and top programs considered? Or also
>verifiable tournament condition games between club players and computer
>programs?

The SSDF has calibrated it's list with human vs computer games.  They also have
used the recent human vs compuer games results to continue to verify the
accuracy of their list.  A couple of years ago they did a re-calibration of the
entire list based the the most recent results.

The callibration results and my list of human vs compuer games are located on
Tony's page.

These games include players of varying skill, Last I checked it was between 2000
and close to 2800 ELO.



This page took 0 seconds to execute

Last modified: Thu, 15 Apr 21 08:11:13 -0700

Current Computer Chess Club Forums at Talkchess. This site by Sean Mintz.