Author: Sune Fischer
Date: 09:14:47 01/17/03
Go up one level in this thread
On January 17, 2003 at 11:53:44, Uri Blass wrote: >>Formula please? > >There should be investigation to find the best formula but even without >investigation I can give you a better formula. > >For example it is possible to decide that if the last opponent that you play win >rating in the next game you get a small bonus of 1/1000 of his(her) gain and if >he(she) lose a game you also lose 1/1000 of the loss. > >The point is that rating is only an estimate and if you see that a player win >rating then the estimate was probably wrong so your rating can change. > >1/1000 is probably too small and it is possible to find a better coefficient but >I suggested a small coefficient only to show that it is possible to get better >rating than the rating that is used today. I think it would be a mess, and I am not sure it is better, you have to be careful that you don't create a "rating canon". That could happen like this: You are underrated by 100 points, you win a tournament and gain the 100 elo. Now your opponents must (on average) be a little underrated, so they now go out and win back rating (on average). This will now push you above your real rating. > >Even with humans if you see that a stable 1600 player who did not play in >tournaments in the last 6 month beat 5 1800 players in a row there is a reason >to suspect that the player learned something and it is not luck and this suspect >should be used to get better estimate. Often there are bonuses for doing unexpectedly well. IIRC we use something like a 30 Elo point bonus for every 1 point above your expected score. The idea is that it's more likely that you are the one that have improved, than all the others have gotten worse. That works fine in a tournament, but not as well on ICC where it is just one game at a time. >If you see that the player beats 2600 players instead of 1800 players then your >suspect can be changed and you can suspect that the player is cheating by a >computer program. Huh?? >It is also possible with humans that the average of the same team go up because >humans learn. Yes but humans also retire and stop playing at some point, that loses rating from the pool so the average on a large scale is pretty consistent. >I see no reason to assume that the average is the same but if you want to assume >it there is no problem. Would you then assume it goes up or down? If A meets B and A wins a lot of games, how can you say it is A that has improved, couldn't it just as well be B that got worse? Your best guess is that it's a little bit of each, one goes up the other down. >You can reduce rating from everyone and keep the average the same. This is what is done, the winner goes up, loser goes down. If that means the loser has now become underrated he can regain the rating by playing other players and thus diffuse the loss to the rest of the pool. -S. >Uri
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.