An interesting 2006 pdf report says, ”We extend the Bayesian skill rating system TrueSkill to infer entire time series of skills of players by smoothing through time instead of filtering." I don’t know what all that means and certainly don’t understand the math given, but the short version is that it’s another attempt to determine the best players of all time. From the paper:
"Estimating players' skills in retrospective allows one to take into account more information and hence can be expected to lead to more precise estimates. Probably best known in the chess community is the Chessmetrics system, which aims at improving the Elo scores by attempting to obtain a better fit with the observed data. Chessmetrics is not a statistically well-founded method and is a filtering algorithm that disregards information from future games.
Looking at individual players we see that Paul Morphy (1837-1884), is particularly strong when comparing his skill to those of his contemporaries in the next 80 years. He is considered to have been the greatest chess master of his time, and this is well supported by our analysis. Garry Kasparov is considered the strongest chess player of all time. This is well supported by our analysis. In fact, based on our analysis Kasparov is still considerably stronger than Vladimir Kramnik but a contender for the crown of strongest player in the world is Viswanathan Anand."
Research-Microsoft
No comments:
Post a Comment