Chess Ratings - How They Work

  • erik
  • | Aug 23, 2007
  • | 224414 views
  • | 505 comments

Like it or not, we ALL have a chess rating. You may not care at all about your rating, or you may be whining every time it goes down in the slightest. You might be someone who plays a game a year, or someone who plays 1,000 a day. Still, there is a number out there that represents how well you play chess. Well, that's the theory, anyway.

To understand chess ratings you have to understand two things: #1 - that you have a TRUE rating that perfectly represents your strength of play, and #2 - that that TRUE rating will never be known and so we have to use statistics to get as close as possible to the truth. I'm writing this article in response to many people who ask about ratings and need a simple explanation of how they work. (I only know about all this because of a recent super-in-depth statistics course I took and my research in building Chess.com!)

There are two main rating systems, and each one has its merits.

The Elo System (used by the United States Chess Federation, FIDE, and many other online chess sites) is popular for two reason - it has been around for a long time, and it is simple. The idea is this: given two chess players of different strengths, we should be able to calculate the % chance that the better player will win the game. For example, Garry Kasparov has ~100% chance of beating my 4-year-old daughter. But he may only have a ~60% chance of beating another Grandmaster. So when playing that other Grandmaster, if he wins 6 games out of 10, his rating would stay the same. If he won 7 or more, it would go up, and 5 of less, his rating would go down. Basically, the wider the spread of the ratings, the higher percentage of games the higher rated player is expected to win. So to calculate a person's rating after playing a few games you calculate the average ratings of his opponents, and then how many games he was expected to win, and then plug it into a formula that spits out the new rating. Simple enough. Well, it turns out, that is maybe TOO simple.

The Glicko System (used by Chess.com, the Australian Chess Federation, and some other online sites) is a more modern approach that builds on some of the concepts above, but uses a more complicated formula. (This only makes sense now that we have computers that can calculate this stuff in the blink of an eye - when Elo created his system they were doing it on paper!) It is a bit trickier than the Elo system, so pay attention. With the Elo system you have to assume that everyone's rating is just as sure as everyone else's rating. So my rating is as accurate as your rating. But that is just not true. For example, if this is your first game on Chess.com and you start at 1200, how do we really know what your rating is? We don't. But if I have played 1,000 games on this site, you would be much more sure that my current rating is accurate. So the Glicko system gives everyone not only a rating, but an "RD", called a Rating Deviation. Basically what that number means is "I AM 95% SURE YOUR RATING IS BETWEEN X and Y." (Nerd Fact: In technical terms this is called a "confidence interval".) If this if your first game on Chess.com I might say, "I am 95% sure that your rating is somewhere between 400 and 2400". Well that is a REALLY big range! And that is represented by a really big RD, or Rating Deviation. If you have played 1,000 games and your rating is currently 1600 I might say "I am 95% sure your rating is between 1550 and 1650". So you would have a low RD. As you play more games, your RD gets lower. To add one extra wrinkle in there, the more recent your games, the lower your RD. Your RD gets bigger over time (because maybe you have gotten better or worse over time - I'm just less sure of what your actual rating is if I haven't seen you play recently). Now, how does this affect ratings? Well, if you have a big RD, then your rating can move up and down more drastically because your rating is less accurate. But if you have a small RD then your rating will move up and down more slowly because your rating is more accurate. The opposite is true for your opponent! If they have a HIGH RD, then your rating will change LESS when you win or lose because their rating is less accurate. But if they have a LOW RD, then your rating will move MORE because their rating is more accurate.

I wish there was some simple analogy to explain all this, but there isn't. It all comes back to this: you have a theoretically exact chess rating at any given moment, but we don't know what that is and so we have to use math to estimate what it is. There are really smart people out there who work on this stuff for a living, and at the end of it all we get to put their proven methods into our code so that we can all enjoy knowing what little numbers next to our name we deserve.

If you want to read more, check out these articles (WARNING - SEVERE NERD CONTENT AHEAD):

- The Glicko System by Professor Mark Glickman, Boston University

- Introduction to Chess Ratings (Elo mostly) on About.com

Comments


  • 3 weeks ago

    WeRfriends

    cannot find the resign button. Any idea?

  • 3 weeks ago

    bravegrape

    play games

  • 5 weeks ago

    soldierjoe3446

    i want to be rated not unrated,how do i do that?

  • 2 months ago

    SpankYoHiney

    btw, wouldn't it be appropriate to have displayed the formula?

  • 2 months ago

    SpankYoHiney

    LeenvdBijl makes a good point.  many games are lost by only a few seconds even though you were spanking hiney!  This is very relevant to me because I'm older and my hand won't keep up with my brain sometimes.  Also, many of us have shaky internet quality, which contributes mostly to our loses.  So, if you have bad internet quality like I currently do, you can be comforted that your actual rating is a bit higher! (lol, i'm being more humorous than serious btw)

  • 3 months ago

    sober10

    How do I avoid playing "unratted" players?

  • 4 months ago

    Poemander

    When two people play chess with each other, one factor concerning their relative strength alone can be measured . Probability? Two gents over six months play every day and one wins two games per loss. A real rating, mathematically derived, would cause ratings to converg over time such that a rating difference implies a probability. The hyperbolic tangent curve, translated and scaled, should represent the relationship between a rating difference and a probability. What more is needed. The asymptotic nature of the curve, at exponential rate, truly depicts the impossibility of greatly mismatched players causing an upset. ELO ratings are linear, not logarithmic, and therefore create inconsistent results. Statistical bandaides do not heal shaky foundations. FIDE seems to have hoped for 10 years that a better theory may emerge. The real mathematics will be derived directly from a consideration of probabilities and the hyperbolic tangent curve. This hypothesis can be contested in practice using a derived theorem:

       If A wins m points per loss against B, and B wins n points per loss against C, then A wins mxn games per loss against C.

     Note that this may be taken as hypothesis and the hyperbolic tangent then derived, but it well explains the novice's chances against the World Champion!

  • 4 months ago

    LeenvdBijl

    I have a problem with higher rated opponents timing out. My rating goes up even though I was losing. Why does chess.com not simply adapt ratings according to the standing of the game at the point of time out??

  • 5 months ago

    bluefirex24

    Is there a site/artical on the statiscitcs on the players average elo on chess.com? How many people on chess.com have a Elo of 900, or how many players out there have 2400 elo? I currently have an Elo 1360 in "Standard" and I want to know where I stand in this ratio.

  • 6 months ago

    MarcoBR444

    I found a very interesting site:

    See the new thread I created below

     

    Find your REAL ELO rating: ELOMETER.NET then post here the results

    http://www.chess.com/forum/view/general/find-your-real-elo-rating-elometernet-then-post-here-the-results

  • 7 months ago

    FreeSolo

    How many games would it take to get a true estimate of your rating playing on Chess.com?

  • 8 months ago

    mannekenpis

    Thanks a lot for the article. It is very interesting and it is getting lots of comments... we love those numbers next to our name, don't we?

    I have got a couple of questions for members or for staff: It is about the computer in the chess.com app. It is ELO rated like, Level 6 1400. How is its strength evaluated? Is it quite reliable? Is it blitz, rapid or classic rating? I mean, if I beat Level 6 my ELO would be 1400 or above?

    I have also noticed that my chess24 rating is about 200 higher than my chess.com rating in blitz, rapid and classic. Which one do you think is more accurate?

    Thanks :)

  • 8 months ago

    kuloiat

    The second link is dead Tongue Out

  • 8 months ago

    bgjettguitar

    The ratings routine may be salient to a more nitpicking personality and I am not blasting anyone with such a minutiae mindset. I'm here for the challenge and to learn and win a game on rare occasions. Someone previously remarked that the score or rating ordeal totally threw them into some kind of morbidity - wholly tossing the very reason for engaging in the game as well as life into a nihilistic fatuity of sorts! That's off the hinges, Chessboard! If one wins all the time, they likely aren't being challenged or perhaps they are beyond Chessgeek reproach! Purely conjecture! Being easily wounded by these numbers is tantamount to playing the guitar like George Benson by ear but refusing to play out because someone was critical about dudes that can't read music. Enjoy yourself, Canker Sore! God bless us! BGJ. NN4P ham geek too :)

  • 9 months ago

    mortega2

    Great article. Very helpful!

  • 10 months ago

    cusanusnicolas

    Still don't know if my rating tells how smart I am. Or stupid! Probably better off not knowing! haha

  • 10 months ago

    samuel_r900

    Good stuff!
  • 11 months ago

    wzupyou

    The ratings are very important for all the people who claim they aren't. For example, I would rather not waste my time playing someone who is 100+ points below my rating. Playing someone so much lower only hurts my game and had no benefit. The only way to get better is to play someone who is a close match up or someone better. For the guy who asks about tennis players... yes, all tennis players have a world ranking and it is affected by how they play other ranked players. You're ignoring the obvious if you don't want to know your ranking. It is very beneficial to know.

  • 11 months ago

    Collin1965

    I think rating sucks. Why? Simple. Are tennis players losing points on the tour when losing a game? Do soccer players losing points in a competition when they lose a game? Or in any other sports? Also i noticed some players increase a lot in rating in one day. So they must cheat. So rating does not say anything about a player, and should not be used in tournements on chess.com. I was put in tournements below 1200 in which i met players who were higher qualified. But it was never corrected. So i think someone should work on this.

  • 11 months ago

    TheronG12

    byzzo-SK, it doesn't really make any difference in the long run. If you're playing at a higher level, your rating will increase anyway after you win a few games.

Back to Top

Post your reply: