which program is best to predict rating based on pgn?

[Uri Blass]

I remember reading at the time of Fritz3 in 1994 or 1995 that Fritz3 had a function to calculate rating of humans based on pgn but Fritz3 was not good in this task because it calculated only 2100 based on pgn of kasparov when it calculated something like 3000 based on pgn of Fritz3
when Fritz3 on p90 of that time was clearly not better than 2450.

I would like to know if today there are better programs to calculate rating of humans based on pgn of their games and what is the maximal error that they get(assuming that they get at least 20 games of the player).

Uri

[swami]

I think there are only few elo ratings calculator available, right? namely built in chessbase calculator, Elo stat and Bayes Elo. Popular ofcourse, is Bayes Elo.

[Uri Blass]

I think there are only few elo ratings calculator available, right? namely built in chessbase calculator, Elo stat and Bayes Elo. Popular ofcourse, is Bayes Elo.

I mean rating estimator and not rating calculator and the program should get games of player X without rating and names of the opponents and get an estimate for the rating of X.

Uri

[Dann Corbit]

Chessbase has a function to read a PGN file and calculate Elo for the players based on the games in the file.

BayesElo does the same thing.

I guess what you are really asking is "Is there a program that can look at the *moves* of a small sample of chess games and estimate Elo based on the moves made?"

If that is the question then I guess that no program can do it.

[Uri Blass]

Chessbase has a function to read a PGN file and calculate Elo for the players based on the games in the file.

BayesElo does the same thing.

I guess what you are really asking is "Is there a program that can look at the *moves* of a small sample of chess games and estimate Elo based on the moves made?"

If that is the question then I guess that no program can do it.

I mean to the last question and it is not correct that no program can do it.

No program can do it well but I remember that Fritz3 could do it.

[bob]

I think there are only few elo ratings calculator available, right? namely built in chessbase calculator, Elo stat and Bayes Elo. Popular ofcourse, is Bayes Elo.

I mean rating estimator and not rating calculator and the program should get games of player X without rating and names of the opponents and get an estimate for the rating of X.

Uri

I do not believe there is such a program that produces anything more than a SWAG with respect to rating based on PGN games without opponents to compare the game results with. Analyzing a PGN game to discover someone's Elo is not something that has been done with any success at all...

[bob]

Chessbase has a function to read a PGN file and calculate Elo for the players based on the games in the file.

BayesElo does the same thing.

I guess what you are really asking is "Is there a program that can look at the *moves* of a small sample of chess games and estimate Elo based on the moves made?"

If that is the question then I guess that no program can do it.

I mean to the last question and it is not correct that no program can do it.

No program can do it well but I remember that Fritz3 could do it.

Chessmaster could annotate games. And it produces babblefish-type output in doing so. So nobody cares if "a program can do it" but rather would care if "a program can do it with reasonable accuracy." The answer is "no".

[Dann Corbit]

Chessbase has a function to read a PGN file and calculate Elo for the players based on the games in the file.

BayesElo does the same thing.

I guess what you are really asking is "Is there a program that can look at the *moves* of a small sample of chess games and estimate Elo based on the moves made?"

If that is the question then I guess that no program can do it.

I mean to the last question and it is not correct that no program can do it.

No program can do it well but I remember that Fritz3 could do it.

But you also said:
"it calculated only 2100 based on pgn of kasparov when it calculated something like 3000 based on pgn of Fritz3 when Fritz3 on p90 of that time was clearly not better than 2450."
Which tells me that Fritz3 was not able to do it.
Or it produced utter foolishness that claimed to be of value.
Take your pick.

[bob]

Chessbase has a function to read a PGN file and calculate Elo for the players based on the games in the file.

BayesElo does the same thing.

I guess what you are really asking is "Is there a program that can look at the *moves* of a small sample of chess games and estimate Elo based on the moves made?"

If that is the question then I guess that no program can do it.

I mean to the last question and it is not correct that no program can do it.

No program can do it well but I remember that Fritz3 could do it.

But you also said:
"it calculated only 2100 based on pgn of kasparov when it calculated something like 3000 based on pgn of Fritz3 when Fritz3 on p90 of that time was clearly not better than 2450."
Which tells me that Fritz3 was not able to do it.
Or it produced utter foolishness that claimed to be of value.
Take your pick.

Here's all it can do: Run a typical "annotate" type operation on the PGN, and then count the number of times the player agress with the program, or the player agrees with the program's second choice, etc. Then use that to derive some sort of rating based on previous curve-fitting data obtained by feeding the PGN from a _bunch_ of players of each rating range through the program to see how they match.

It fails for many reasons, not to mention the most obvious which is the hardware is critical. Use slower hardware and the ratings will be over-estimated, use faster hardware and the ratings will be under-estimated.

In short, a SWAG at best, a random number at worst. Neither of which is particularly useful or interesting.

[Dr.Wael Deeb]

Chessbase has a function to read a PGN file and calculate Elo for the players based on the games in the file.

BayesElo does the same thing.

I guess what you are really asking is "Is there a program that can look at the *moves* of a small sample of chess games and estimate Elo based on the moves made?"

If that is the question then I guess that no program can do it.

I mean to the last question and it is not correct that no program can do it.

No program can do it well but I remember that Fritz3 could do it.

But you also said:
"it calculated only 2100 based on pgn of kasparov when it calculated something like 3000 based on pgn of Fritz3 when Fritz3 on p90 of that time was clearly not better than 2450."
Which tells me that Fritz3 was not able to do it.
Or it produced utter foolishness that claimed to be of value.
Take your pick.

Here's all it can do: Run a typical "annotate" type operation on the PGN, and then count the number of times the player agress with the program, or the player agrees with the program's second choice, etc. Then use that to derive some sort of rating based on previous curve-fitting data obtained by feeding the PGN from a _bunch_ of players of each rating range through the program to see how they match.

It fails for many reasons, not to mention the most obvious which is the hardware is critical. Use slower hardware and the ratings will be over-estimated, use faster hardware and the ratings will be under-estimated.

In short, a SWAG at best, a random number at worst. Neither of which is particularly useful or interesting.

I am quite surprised that an experinced programmer like Uri asks such a question....thinking less than a second,I knew that there is no such program....