Vote for the old rating system

many people are unhappy with the new ratings........including me. so, where are the fans of the new system ? i want the players to vote for their favored system. how about you ?

I don't really mind new or old personally. Ratings are just numbers to determine the best opponents to pair against. I think it was done to make the ratings more stable. Probably going to be the same deal as v2 once it's done, it's done.

The old system is better. The "new" system does not reward a player when he/she is on a hot streak .

#1 Good grief... I don't understand.

#3 The most common complaint about rating in the IRC, Discord, forums, and Twitch is that players were avoiding low-rated opponents for fear of losing many rating points. And rightly so, as ratings were unstable.

I like the stability.

Why get so worked up about 3 fantasy points more or less per game?

Try to improve your chess, not your points. The points will adjust to your skill sooner or later anyways.

#6 Well said! I also like the new system with RD=50,as ratings are stable and represents each player's chess skill level decently.Another advantage is that sandbagging is now harder with the new rating system.

Am I blind? What's the new system and where can I read about it?

There are a couple of threads about that in the last 2 weeks, @edvindracula .
But it is not really a big thing. One parameter in the Glicko calculation has been adjusted to the frequency of recalculating the ratings as it is done in Lichess. So our ratings don't jump up and down so extremely anymore.
And it is not a matter of voting but a matter of statistical mathematics as far as I have understood. If you never noticed, never mind. if you look at the rating graph of frequent players (as mine), you will detect it became smoother in the last 10 days or something rather than a very unsteady zig zag line before.

The short version: ratings should have predictive accuracy. Having random ratings doesn't make sense. (As I again reread http://www.glicko.net/glicko/glicko2.pdf I think the RD >= 30 in Glicko-1 is unnecessary in Glicko-2 because the volatility term already accounts for improving or declining players. However this raises a question about Glicko-based systems with undefined rating periods and whether volatility terms are stable. As an aside... I've been beating a dead horse about improving Lichess rating system in this forum for years, and only now do people care to chime in... I suppose not everyone reads the forums.)

Thanks to gcp for this analysis/simulation: github.com/ornicar/lila/pull/4034#issuecomment-433472996

Because the RD(phi) increase is applied after every game instead of every rating period, Glicko-2 has much higher RDs by default, causing the ratings to flobber about much more. Empirically, on lichess the majority of players never go below RD=60, there's maybe a dozen or so in my entire dataset (mostly because they managed to get non-default lower volatility, which is also very rare).

After removing the RD >=60 limitation, or putting it to >= 30 (as recommended in the Glicko-1 paper), the prediction performance of this pull (Glicko-2 + sigma scaling over time, aka Lickgo-2) beats Glicko-1 and it's a strong improvement over the current Glicko-2 ratings.

Limiting the RD to 30 or not limiting at all seems to make very little difference [in terms of predictive accuracy]. In general it will grow quickly unless the player is playing a ton of games, in which case their rating is constantly adjusted anyway. So the limit probably just isn't necessary at all.

Glicko 1 prediction rate 56.591%, MSE=0.2250
Glicko 1 (no RD cap) prediction rate 56.618%, MSE=0.2250
Ligcko 2 prediction rate 55.483%, MSE=0.2269
Lickgo-2 (no RD cap) prediction rate 56.729%, MSE=0.2248
lichess prediction rate 55.122%

So, if the minimum RD gets lowered to 30, or removed entirely, it would clearly improve the accuracy of lichess ratings.