Author: Robert Hyatt
Date: 19:21:09 03/17/99
Go up one level in this thread
On March 17, 1999 at 17:43:21, KarinsDad wrote: >On March 17, 1999 at 13:35:46, Robert Hyatt wrote: > >[snip] >> >>this is another interesting aspect. The "K-factor" in the rating calculation >>was arrived at most likely by 'trial and error'. IE it was tuned for tournament >>chess where you might play 5-10 games per month, and K has to be large enough to >>let your rating swing as much as it should. But what if you play 100 games per >>day. I'd almost think K should shrink _way_ down... ie as in the "glicko" >>rating system that is _much_ more stable. IE what is the probability that >>Crafty is actually 200 points worse than yesterday, when _no_ changes have been >>made? Very low. Yet if I play an equal-rated player, my rating changes by >>+/- 16 after one game. For a server, I believe this is _wrong_. > >Robert, > >Are you saying that the servers do not decrease the ratings changes (i.e. halve >them just due to the fact that a higher rated player is playing) for the higher >rated players? > >If so, this is strange and disturbing. > >KarinsDad :| No... the Elo system has a 'max change' paramater K, that seems to be set to 32 for most places. And that works well in that the most your rating can change with any one game is 32 points. But it is proportional to the rating difference between you and your opponent. Other servers use a smaller K (chess.net for example) as suggested by the 'glickman' proposal for rating calculation. If you reduce K, then you reduce the maximum rating change delta. and you limit rating 'swings'...
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.