Thank you dead stick, I appreciate it.
Questions for Mike with FargoRate
- Thread starter Tin Man
- Start date
DaWizard
Well-known member
Are there some interesting numbers in the mountain of data? Extreme rises? Biggest upset? Surprising things? Odd things?
I also really like the features as suggested by @DeadStick.
Those would make it an application to regularly check, share interesting data and detect sandbagging. But mostly I think people will spend more time in the app.
I also really like the features as suggested by @DeadStick.
Those would make it an application to regularly check, share interesting data and detect sandbagging. But mostly I think people will spend more time in the app.
Last edited:
That’s wild that you think that.
1. Have you ever run any numbers on snooker? I would be especially interested in Ronnie O'Sullivan's rating.
2. Ever thought about renaming it? Not that I have a better name in mind, but when I bring it up to friends of mine outside of pool they are always surprised by the name. No -- don't switch it to 'X'.
3. Do you feel you've won over the players? I do as I hear less and less stupid complaints from players who are trying to manipulate their rating and more prideful talk about where they've gotten theirs.
2. Ever thought about renaming it? Not that I have a better name in mind, but when I bring it up to friends of mine outside of pool they are always surprised by the name. No -- don't switch it to 'X'.
3. Do you feel you've won over the players? I do as I hear less and less stupid complaints from players who are trying to manipulate their rating and more prideful talk about where they've gotten theirs.
I tend to agree. Certainly there are people who are more comfortable on one than the other, but if somebody is significantly better on a bar box, ultimately they're going to be better on the large table too.
600's don't start getting their asses kicked by 500's just because they move from one table to another...
Lowering your FR is harder than you'd think. Maybe a few points here and there but not much. That's why these events usually require robustness of 500, the more games played the more accurate the FR.
That actually does happen. At one point the number of 800 players was very low, I think there was one one at some point, SVB. Maybe my memory is off on that, but I remember the max being in the very low 800s. I have also noted players not playing for a year but their Fargo changes, because the players they are linked to change, so the saying the tide lifts all ships is true in Fargo. Sometimes not fairly hehe. The guy that was a 500, then quit playing and comes back to find he is a 520 because the other players he played with kept playing is in trouble. For Fargo to stay highly accurate, the players have to stay active so their results against those that go up or down are adjusted.
That just means those players don't have the results entered in Fargo, or they will be going up. Or your idea of "really good" players is different from the norm. Fargo does not just watch every match of every player on the planet, someone has to enter matches into the system, so playing for 10 years does not mean anything. Only the results of games entered in Fargo matter. If those players have like 20 games in Fargo it can easily be incorrect.
Since athletes improve overtime, I would think it would be the other way around the player that was 600 ten years ago might be a 570 today
IDK.....I went 2 years without playing a Fargo match.....My Fargo went up in those two years.
The problem (as I see it) is that the TDs are using Fargo to limit the field.....If a tournament is capped at 599 and under.....How are those players going to get a Fargo above 599?
Also....playing in capped fields....limits your growth.....Way too many innings in a 599 and under match......The top guy in the field 599 gets good at playing "clean up"....and may even not care if the other guy shoots in the beginning of the rack....He/She knows they will get another shot at that rack......Then they finally step up to play a 700 player and get destroyed.....Missing a ball early may cost you multiple racks (if not the match).
EDIT:I know "why" TDs do it....still sucks for growth of the game
600-640 is no mans land around my neck of the woods.......Too good to play in the soft tournaments.....get pummeled in the open tournaments.
If we ignore sandbagging.... There are two sources of error in a player's FR.
Random fluctuations can be figured out from the robustness, but how large is the expected error versus number of games recorded? Is there a secondary effect due to the lack of robustness of a player's opponents?
A second is due to the improvement (or decay) of a player's game over time. A new player who has shown a lot of improvement over the last several years is probably underrated. How large is that "lag" error for a typical new star?
Also, I was wondering if there were any observed "islands" of players -- a group that is weakly connected to the larger world of pool players. Recently a Peruvian player (Gerson Martinez) appeared from nowhere, or at least I hadn't noticed him before. Is Peru an island?
Random fluctuations can be figured out from the robustness, but how large is the expected error versus number of games recorded? Is there a secondary effect due to the lack of robustness of a player's opponents?
A second is due to the improvement (or decay) of a player's game over time. A new player who has shown a lot of improvement over the last several years is probably underrated. How large is that "lag" error for a typical new star?
Also, I was wondering if there were any observed "islands" of players -- a group that is weakly connected to the larger world of pool players. Recently a Peruvian player (Gerson Martinez) appeared from nowhere, or at least I hadn't noticed him before. Is Peru an island?
TL/DR: Drift happens. Deal with it.
Long answer:
Regarding overall rating drift (aka inflation or deflation) over time, I think Mike would explain it along these lines:
The FR system was based on ELO theories developed in the late 1950s and adopted by the worldwide chess community in 1970, so there is LOTS of history and experience they can draw on from chess.
Chess has seen both a drift upwards, and downwards, in #1 ranked player ELO ratings over time. A lot depends on the influx and outflux of players. In a closed system, with no new players entering or leaving, the average ELO (or FR) will stay constant, since when one player wins at a margin of victory higher than expected, his rating goes up, his opponent’s rating goes down by the same amount.
If SVB is at the top and keeps beating players beneath him at or above his expected margin of victory, he will keep going up and others will keep going down, maintaining the average. That can’t continue forever, because the opponent pool’s lower rating means SVB will need to keep winning by larger and larger margins to continue rising.
New players start low, typically, then some of them rise through the ranks. The usual drift in the overall average is downwards, since new players come in low, while higher, more experienced players exit at higher ratings.
Chess has made several attempt to control the drift, but it’s a tough nut to crack. You can read a detailed analysis of it all here: https://woochess.com/en/blog/elo-ratings-variation-in-time
BOTTOM LINE:
The goal of ELO/FR systems is to maintain an accurate rating system for RELATIVE player strength at any point in time, not ABSOLUTE player strength over time. Why? Because the main priority of the system is to accurately handicap matches, and the FR system is designed so that 100 points is equal to 2X player strength, on a logarithmic scale. If drift happens, it’s because it needs to happen, due to shifting player counts in and out and the distribution of relative skill levels.
You can’t say that an FR750 player 10 years ago was the same strength as an FR750 player today, even if the top rank numbers stayed the same. There’s just no system that could tell you that, since the opponent pool changes over time.
And if you stop playing reported matches for 10 years as a 600, your score could drift up or down with the tides over time, just like there is drift effect over and above your match results if you stay active.
Last edited:
This statement assumes the players never practice or play outside of those tournaments. If you beat a 599, you are over a 599. Eventually over time if a 599 enters the event, and is showing beating players by a good amount, they will go over 599. It does not matter who you play, it matters by how much you beat them over a long period of time. If you are playing ten 500 Fargo players over 100 games and are beating them at a 60-40 ratio, that shows you are a 540 or 550. If you are beating them 70-30, you are a 575. And so on. If you are playing a 599 over a few tournaments and end up winning more and more, your Fargo will go up over 599 based on by how much you won. Keep in mind this is a period of many dozens or hundreds of games not a few tournaments.
The question is whether a player playing ONLY in bar box (BB) tournaments and achieved a 500 FR is of equal strength to player playing ONLY in regulation table (RT - 9 footers) tournaments and achieved a 500 FR. I believe the answer based on arguments presented here would be YES because “It’s not rocket science - it’s just math based on actual matches.” However, I believe this would be correct ONLY if you have a homogeneous database where the vast majority of players play both BB and RT tournaments. However, if for example (just to test the limits) we have a database where we have 7/8 of matches recorded played on BB by players who ONLY play on BB and 1/8 played on RT by players who ONLY play on RT, the median will be heavily skewed by the BB players and the median player will not be a true representation of ALL pool players.
Put another way, if we had two systems where one calculated FR for only BB tournaments and another FR for only RT tournaments would it be reasonable to say that a players with a FR of 500 on BB is of equal strength to player with FR 500 on RT?? I don’t believe so.
From my personal experience, I don’t think it’s a stretch to say that the vast majority of players play only on BB or FR. You cannot get most of the league players to play on a RT. If you ask them to play they look at you like if you are from another planet LOL. On the other hand, the RT players think that playing on BB is a waste of time.
I think what Mike came up with is a lot stronger than chess ELO. There was a prisoner in the 1980’s-90’s who ended up ranked #1 or #2 in the world, right with Gary Kasparov. He manipulated the system (within its rules) by only playing fellow prisoners. Chess ELO from my understanding takes and gives points per pairing of a match. Whereas FargoRate recalculates every single game daily, to find the best fit of all players/data.
Or you can ask "what happens if a player ONLY plays 3 other players that are blind", and he ends up being like an 800 Fargo because he beats them 10-0 every match. It's only valid for a short time in a bubble of rating till any new data is introduced.
Mike showed that the isolated cases where players don't interact with different table sizes is pretty much at 0. Even if 20 players in Dallas only played on 7 footes, the 21st guy played on 9 footers in Houston and has a set Fargo. He starts playing with the 20 guys in Dallas and their are linked to his rating. Finding a group of players to argue validly about the 7 ft 9-foot skill level that ends up being correct statistically is like finding a tribe on an island that never had contact with modern man. Fargo does not give a crap about a single player or a group of 10 players or 20 players, it rates thousands of players over hundreds of thousands of games and presents a statistical prediction based on the average of all of that. It's like an insurance company that sets rates, they know that a person with a single accident has a greater chance of having more than someone that has not had one at all, so they automatically adjust the cost based on that. If you go argue with them because you can show them that your mom and uncle had only one accident that never had another, they will show you the 134,567 others that had one accident then had another one the same year.
Long term statistics and data trump small personal experiences and "feeling" and theoretical situations. For every Brumback that can be pointed out as an exception being amazing at one game but just OK in others there are 20 Gorsts or Fillers that are equally good at most games. Same thing for Joe Billy Bob that is a 600 at a 7 footer but can't make 3 balls on a 9 footer, that is super rare and just gets lost in the noise of statics.
Last edited:
tomatoshooter
Well-known member
I think they would match up well. BB player is probably better at breaking up clusters and navigating tight position, RT player is probably better at long shots and longer multi rail routes. At 500 there may be a difference, but much higher than that I think you need a complete skill set and the difference would be smaller.
Yes. The Elo system (developed/popularized by a man named Arpad Elo) has much, much simpler calculation involved. At the time it was developed, it was about all that was possible. I'm not sure but I think Elo doesn't look much at robustness.
Recalculating FargoRate ratings takes hundreds/thousands/millions of times more calculation but that's easy these days.
Has the chess world moved on from ELo and into the Glicko1/2 system? Or are they still using Elo?
Parts of it but not the main organizations. https://en.wikipedia.org/wiki/Chess_rating_system