As an AI enthusiast, this is exciting. As a Football fan, this is a concerning trend.
Usage of technology has ruined several aspects of traditional association football. The VAR for example, is ruining the serendipitous nature of football. Fans in general dislike the VAR because it removes this extra element of drama that the sport has.
I’m supportive of technology in sports though. I just think there should be a limit, otherwise they become a very boring and cold activity.
I’m not necessarily against the suggested approach here. Having analytics of how a game is going or went seems useful and a net positive.
It’s just hard to tell if that could keep eroding those entertainment elements that make Football fun to watch.
I wouldn't really be concerned. This new element basically changes coaching and recruitment, not so much the actual play. Unlike basketball, football is open enough to not have an easy to prove maximizing strategy (unlike basketball, with the emphasis on 3 pts shooting).
the 3-pointer by itself isn’t point-maximizing, and surely doesn’t assure victory. the point-maximization is only valid in the context of the current game aesthetics. if a team tried to shoot only 3-pointers, they’d almost certainly lose because the counter-defense becomes simple. only by mixing shot selection does the 3-pointer’s slight advantage matter, and it’s not enough of an advantage to trivialize the game. it does what it was meant to do, which is inject unpredictability/variety into both offense and defense, especially at the end of close games, for more interesting and exciting gameplay.
Of course I simplified the issue, but my main point is that in football there isn't an equivalent to the 3 pts advantage in basketball (however slight it may be).
Of course, but the reality is that analytics have proven that there are only really two shots worth taking in modern basketball: the 3 pointer and a shot near the rim. For anything in between the expected points for the shot is simply not worth it. Even an uncontested midrange shot is going to have similar or fewer expected points per shot than a contested 3-pointer or shot beneath the rim. And these two kinds of shots are spatially far from each other, so even if the opposing team knows this is your strategy, its still difficult to defend against. Teams and players that have tried to exploit the fact that modern basketball is fairly homogenous by taking relatively less defended midrange shots occasionally find streaks of success, but it hasn't proven sustainable, and certainly not enough to win a championship.
Basketball would probably benefit from either eliminating the 3 point shot, or, perhaps preferably, pushing the line back a few feet to even it out in terms of point expectations with midrange shots. Shots under the rim will still remain the most reliable point source, but teams won't have to divide as much attention on getting steam-rolled by three pointers. It will bring back scoring big men like a prime Shaq who have mostly disappeared from the game, still allow phenoms like Steph Curry to thrive (fewer players can match his ability to hit 3-pointers from further distance), and will make the midrange focused strategies more viable again.
A lot of teams still get their points inside the perimeter. Look at Zion Williamson for example. Injured now, but most of the Pelican's points come through him, and it's only going to become more worthwhile to do it, and build a team around the fact that he almost guarantees two points every other possession.
The strategic trends always go in and out of fashion.
One thing that I see in Basketball that needs fixing though, is that the rules make the defender's job incredibly hard. Especially with the rules around fouls. They need to look into fixing that. I think a solution to that class of issues, will inadvertently fix the 3 pointer issues you cite too.
> A lot of teams still get their points inside the perimeter. Look at Zion Williamson for example.
Yes, but by "inside the perimeter", you mean up-close to the basket. Zion is a great example. Take a look at his shot chart [0]. He doesn't even think about shooting more than a few feet away from the rim.
As I said, at this point, basketball has coalesced around offenses entirely focusing on shots at the rim, or beyond the 3-point line. Anything between there is a wasteland where teams don't even bother shooting anymore, despite Hall of Fame players like Michael Jordan and Karl Malone making those areas of the court a huge part of their game in the 90s. And this doesn't seem like much of a fad. Its a trend that has been becoming increasingly entrenched for nearly 2 decades at this point. The charts on this 538 article are all you need to see why this isn't simply a matter of what's fashionable, and is a simple mathematical reality under the current rules [1].
But I definitely agree with your last point. Basketball has numerous issues currently, of which unequal shot efficiency is only a part.
no, the midrange shot is exactly the shot that propels teams to championships, as the rockets of the past 5 years learned the hard way, so much so that d'antoni was demoted and harden moved on to a superteam with great midrange shooters (durant & irving). and as great as curry's shot is, the warriors are unlikely to make the playoffs this year. the midrange plays a specific strategic role, and teams pull it out especially for the playoffs.
the playoffs are all about effective shot selection, with the midrange becoming prominent because defenses tighten up arond the perimeter and the basket. lebron and anthony davis both explicitly featured their midrange game in last year's championship run. the clippers, incidentally, have the best midrange shooter (kawhi) and lost early last year because they relied too much on the 3-pointer. even the warriors of old used the midrange shot to keep defenses guessing enough to give their shooters space to shoot.
and that's exactly the issue with relying too heavily on analytics--humans aren't static, and pinning down the exact parameters where a model is valid is seductively elusive. mathematical models don't so much tell us about how the world is, but rather more about how the modeler sees the world. models aren't useless but they are limited (really knowing how is the hard part).
I think the causation here is kind of backwards. Those teams are good because they have the best players that shoot well in any range. But looking at Kawhi’s shot chart [1] indicates he should be shooting more 3’s as defenses still keep him to below 1 point expected per mid range shoot vs. more than 1 point in 3 range.
what's missing is that those things are correlated. kawhi wouldn't have the 3-point percentages he has without the midrange threat to loosen defenses. and the best players are the only ones trusted with midrange shots (even on lesser teams--derozen & jimmy butler for example). role players are expected to only take 3's or layups. that's the aesthetics today.
Baseball has been grievously harmed by the numbers. Too many strike outs and home runs, and the shift has just become infuriating. Reading a 6-3 in the scorebook, one has no idea what actually happened.
As a basketball fan, my only gripe with VAR is how much time it takes to complete. Advanced AI would presumably extend into those systems and make the review near instantaneous.
I think the main complaints about VAR in football have been the amount of time these decisions take and the inconsistency of the rulings. Instead of the constant play we used to have, now we see players stand around as the screen shows lines drawn in seemingly arbitrary locations to decide whether or not an attacking player was onside before a goal.
In contrast, fans have been fine with the goal-line technology, which gives decisive (usually) and quick results.
The use of AI in this paper seems more relevant for setting team strategies and picking players rather than enforcing rulings.
VAR could be used in situations where it is quicker.
For example, in basketball, it should be able to do goal-tending in near real time. Also 3s in the key.
The holy grail though is if it can help charge/block calls. Or we should consider changing the rule so that it can be consistently called, but that's a topic for a basketball forum.
> Arrigo Sacchi, a successful Italian football coach and manager who never played professional football in his career, responded to criticism over his lack of experience with his famous quote when becoming a coach at Milan in 1987: “I never realised that to be a jockey you had to be a horse first.”
I don't completely disagree with every point made there, but overall I think the author has trouble defining refinement culture in part because its not so much a coherent idea, and more a rambling rant against things changing. I don't really find most of their post to make any substantial points at all, beyond a few of the points about basketball and baseball.
I agree that those sports have suffered in terms of watch-ability at the hands of maximizing competitive efficiency. But I don't really know why anyone would expect anything different. The point of the game from a team/player perspective is to win. Using analytics to determine that there are advantages to three-point shots or walks isn't any different than any other strategic layer of the game. The solution shouldn't be to rail against analytics (which is no solution at all), it should be for the leagues to use analytics of their own to control for some of these strategies, like a government is supposed to hedge against externalities in an market. For basketball, simply push the 3-point line back a few feet so its no longer so much more advantageous than a midrange jump shot. I'm not much of a baseball fan, but surely the league can do something, like increases the number of balls to walk to 5, that might bring some of the boring-but-efficient strategies into line with more exciting ones.
Though I suspect the author and many others would be against any substantial rule alterations given their abhorrence towards change, and would rather just pine about the good old days.
+1 for "just" changing the rules or ball or whatever to improve (or at least test) game dynamics for greater balance and (presumably) interest.
My personal interest is for soccer to allow more substitutions to let coaches tweak the team more as the game is played. Small change; maybe big results in scoring.
This article is presenting some of this stuff as new when it has been used for years in sports. I haven't read the linked paper yet, so maybe there is some deeper insight there that I am missing in this article, but computer vision, statistical learning, and game theory are all well established in multiple sports.
That’s very broadly true but football (of the soccer variety) still lags a bit behind basketball. The number of clubs using computer vision, or deep learning models on tracking data is probably still in the single digits. Even clubs that do have people capable of doing this (or pay a provider), aren’t necessarily integrating that with their actual coaching or recruitment.
There's nothing jumping out at me as original thinking in this article or the paper abstract that points to the paper being worth more study.
All of what has been mentioned has been conceived of, thought about and discussed before, and some years ago. I've seen more advanced thinking in some models used to make bets on football matches.
As a Man City fan, I'll try and make this sound less snarky than it will come across, but it's going to be snarky: it's good to see Liverpool are finally - with Deep Mind's help - catching up to where many other teams in the league were more than half a decade ago.
Most players and coaches are not particularly interested in these models and the most useful applications seem to be related to scouting and the transfer market - "I need a replacement for player X, but 10 years younger and with a better left foot", is the sort of problem that data science is already helping with - and the clubs themselves prefer to put their money onto the field of play rather than expensive and experimental ML training, so the market for this sort of work is limited.
The challenges in this field are not really about data, algorithms or computational capability of the hardware.
The main issues are of applicability, cultural fit and economics.
Finding methods for addressing _those_ issues might be more useful to mainstream AI adoption than the data, algorithm and hardware problems many seem to look at first.
Sports analytics is an interesting field, worked in it, you can use it for keep tracking of the health of your players.
To know when you need to keep them from playing the next game or stop them from continuing their current game.
Liverpool have been doing this for years without Deepmind’s help (it’s been more than five years since Michael Edwards was decried as a laptop guru who betrayed Brendan Rogers, for example). The analytics team at City Football Group has only really been built over the last year (but are very good). I don’t know that any of their dabbling before that was at this level.
Your point about applicability is totally right though, see Arsenal with StatDNA and the arguably weak impact of Barcelona’s Innovation Hub. I’d argue that Leicester’s use of (at the time) very rudimentary stats, nevertheless well integrated into their process, was a big part of their sudden success.
I knew - and still know - the data guys from CFG who were there in 2016-ish. It's no doubt undergone a lot of changes, but it's definitely not really been built over the last year.
I know Brian Prestidge has been there a while and obviously has stats pedigree going back before even most of the data providers. But I don’t believe he’s been doing most of what Deepmind are talking about here (or which Will Spearman has been working on at Liverpool), which (as I understood it) is why they’re hired people like Laurie Shaw etc over the last year. Happy to be corrected, they all seem like great guys.
Agree with you that figuring out the cultural fit and applicability is super important. I learned a lot firsthand about this while trying to set up a decision support tool (with a supervised learning algorithm underneath) for a few teams in NASCAR back in 2012 [0].
I've done some work in sports analytics for an NBA team, and while I think there is some value there, I also think that most of the low hanging fruit has already been plucked at this point. People have been pointing to the same examples of "Moneyball" in baseball, or 3-pointers in the NBA, for at least a decade at this point. The reality is that for a lot of sports, they are complex enough systems that even if insights are generated, they are complicated enough that its hard to action on them. Look at the animation of the predicted player movement on the field. Its pretty, but what can a manager or player reasonably do with that information? Not a lot. Right now, it seems like most analytics in sports are solutions looking for a problem, which is understandable so many of us in ML and statistics are sports fans. But ultimately, I don't see much impact being made, certainly not on a Moneyball-esque scale.
There are still areas where analytics will continue to be important in sports and player assessment/team composition will always heavily rely on it. However the next steps for sports analytics in my mind are things that go on behind the scenes of the sport: personal training routines for players, managing wear and tear and predicting injuries, etc.
Also, the leagues themselves have lots of room to improve their products with analytics. Many complaints have been raised (which I agree with) about how boring modern basketball/baseball has become due to analytics causing teams to converge on strategies that maximize efficiency but are also quite boring. It isn't on the players/coaches to try something more exciting at the expense of winning. It's the league's job to make the product interesting. Analytics can be part of the solution, like determining that by pushing the 3-point line out several feet, the value of the shot is brought in line with other options that simply aren't viable right now.
If you don't mind my asking, what kinds of models/statistics/analytics did you find most useful? I'm curious because I've done some analytical work for professional League of Legends teams in the past, but have recently been unenthusiastic about pursuing this anymore because my creativity has dried up about what is "useful". I also share your opinion that most of the low hanging fruit has already been done.
Obviously the games are different, but perhaps there are some common themes or generalized structures that can help frame what questions to ask?
There are lots of commonalities between invasion sports - famously one of Pep Guardiola’s coaches at Manchester City is a former water polo player, for example. I assume much of what’s been learned there (minus the ball) applies to games like League of Legends.
So, from what little I know of LoL, you’re simultaneously trying to attack the enemy base and protect your own. Presumably there are interesting second order things to study here - how can you get close to the base, how can you destroy it quicker than the opponent destroys yours etc. I assume if there are any epiphanies along the lines of “shoot threes” in basketball or “shoot closer to goal” in football, they’re probably well trodden.
Much of the game is presumably controlling the space between, trying to create overloads against opposition players, and not be overloaded yourself. The best teams in football are experts at using space, and at manipulating their opponent’s shape to create gaps or opportunities for ambushes. So an interesting thing to study would be teams tendencies to overextend - what sort of structures appear to offer them opportunities, but actually keep your players close enough together to pounce on them. The ghosting work mentioned in the article would be interesting here, as would work on pitch control:
Lol and soccer are extremely different. It's much more analogous to basketball or fighting sports. You want to get more jabs in than your opponent so that when you go in for the kill you have more strength/stamina left than they do. The question is more along the lines of how do we cause the most damage? Preventing yourself from being damaged isn't as important because it happens naturally if you control the tempo.
Would love to hear more about your analytics work in League of Legends. Is it fair to say that the "useful" numbers/stats tend to be low-hanging fruit and not particularly interesting / requiring of creativity? I imagine with a fairly dynamic meta-game, you're limited by the data available to you, which can quickly become obsolete.
I'd also imagine any data you can crunch from solo queue games is of limited use in competitive play.
Happy to share. I’ve worked as an “analyst” which basically has boiled down to creating 15 minute slide decks detailing player behaviors/patterns, which ideally would be used to scout upcoming opponents and look for weaknesses.
The easily digestible stats like KDA or gold/min are relatively useless in this regard which is what I meant by them being low hanging fruit.
So I’m currently in a situation where I’m curious on how to best quantify or develop a series of metrics that can prepare teams for their opponents. The current system of watching vods, taking notes, and making slides is rather dull if I’m being honest...and really not paradigm shifting. If you’re interested I can show you videos/presentations/figures.
I personally did work on modeling injury risk for an NBA team, which at the time was something they hadn't done much with and found very useful. Unfortunately it might be hard to apply that to LoL.
> Obviously the games are different, but perhaps there are some common themes or generalized structures that can help frame what questions to ask?
One of the most important things to understand is what the front office, coaches, and players want to know. Like I said, much of analytics these days (and not just in sports) is a solution searching for a problem. We build models based on what we can with the data, but the output of the models isn't actionable or something anyone is asking for. A better approach is to start from the questions that loom big in the eyes of those you are doing the analytics for. That sounds simple, but often doesn't happen, either because communication is poor, or neither party really understands what the other is trying to do. Also, often times a team doesn't even really know what questions they'd like answered, or at least not enough to verbalize it well.
One thing I've found consistently useful is focusing on measuring uncertainty. These days people are extremely excited about machine learning and "AI", and I work extensively with deep learning in my current position. But most times in analytics, especially sports analytics, simply getting the best prediction possible isn't actually useful. What is far more useful is measures of uncertainty through more traditional statistical methods, especially Bayesian statistics and Monte Carlo simulation. It's one thing to predict a player in the draft will be better than another. But a team usually knows the answer to that already anyways. Its far more useful to quantify the range of possible outcomes for a player. Is it practically a sure thing? Is it not a sure thing but a reasonable bet? Or is it really a toss-up? These are insights that teams often don't have but can find much more useful in their decision-making.
I generally don't focus on in-game strategy, since it is harder to give the team something they don't already know that they can reasonably act on. But meta-game insights could have a lot of potential. For traditional sports, this can be things like assessing player value, injury risk, draft capital, and contract valuation. Some of these may not translate well to LoL. I haven't played the game, but I've watched it a few times, and perhaps something could be done looking for insights regarding the hero pool. There are so many different heroes in the game that can act/oppose each other that quantifying those relationships somehow could be interesting.
Have you looked at improving individual performance/tweaking training plans? Versus more game theory of group games? Or have any research suggestions to read for say a competitive college athlete performance level?
I'd be super interested in that and seems like the more data we can collect from watches etc the more potential variables to model or train ML suggestions on?
lots of companies spending big money on this market too. Apple, pton, smart watches.
The documentary Breaking2 from nike about the marathon is really good, shows some advanced individual measurements that wouldn't be available to almost everyone (lactic acid blood draws while running..). in my sport climbing finding new ways to push lactic acid tolerance or better improving physiology through BFR or whatever training would be really valuable and maybe push the sport even further.
I completely agree that modern analytics has made baseball more boring. More strikeouts, more pitching changes, less stolen bases, more walks, and more pitches per at bat all make the game more boring for sure.
But basketball seems the opposite to me. Analytics has shown that except in a few superstar cases, back to the basket isolation mid range jumpers while the rest of the team stands around and does nothing (IMO the most boring play in basektball), is a terrible play call.
Analytics has shown that the pick and roll is a fantastic play in terms of points expectancy and I find it to be a really enjoyable play to watch because it often results in dunks and nifty passes or acrobatic layup attempts.
Analytics has shown that faster pace, shooting earlier in the shot clock, and getting out in transition more often to be hugely valuable strategies, all strategies that I think are more enjoyable to watch.
The perceived value of 3-pointer shooting has caused offenses to spread the floor creating more driving lines and making it harder for defenses to pack the paint which has created more offense which I think most people enjoy seeing.
I'd love to hear what you think analytics has done to make modern basketball more boring.
It's interesting in baseball (I agree the game is less exciting!) because the new way of playing is optimized for winning games, not for fan enjoyment. To me, this says that baseball's structural balance between pitchers and hitters is fundamentally unstable, with both sides optimizing to increase variance.
Analytics only uncovered these structural issues for teams to exploit. Personally, I think if the strikeout rate were tamed back to 1990s levels, the game would balance.
I believe MLB management agrees with you because they're considering testing moving the mound back a foot which would give hitters more time to react and should help balance the strikeout rate.
The drop in batting average is primarily due to the increase in strikeout rate. Homers are down, but it's the K rate that is the problem. This is a problem because pitchers are better, but also because analytics has taught that strikeouts are the pitchers best friend, while homers are the hitters'. More attempts to hit homers mean less "2 strike swings" as players used to be taught.
The optimal strategy for both sides is for pitchers to go for the K (increases K rate) and for hitters to try and hit the homerun (also increases the K rate).
Sure those are two of the three true outcomes that the pitcher and hitter have the highest degree of individual control over, so how are you distinguishing that the K-rate is the issue compared to the HR%, which as you noted, is also down? From my POV the hitters optimizing for launch angle (long fly balls instead of lower-trajectory line drives) is just the other side of the equation from pitchers throwing hard and going for high K-rate.
They are considering it, but I don't think there's a ton of evidence that it will balance the strikeout rate. It will probably decrease it, but would also possibly increase walk rates as well as potentially increase SP injury.
I find this interesting, as it actually emphasizes baseball's role as a _passtime_. One of the key aspects in sabermetrics is that activities that carry the risk of an out are disincentivized because baseball is not time-limited, but out-limited. Therefore all the activities that are interesting, but carry that extra risk like stealing, are taken out of the game.
Basketball is time-limited, and therefore the strategy of maximizing the number of shots within that time period as well as maximizing their value, make sense.
I'll note that I don't necessarily think one is better than the other, as each game can have a different approach. I also think that maximizing purely for excitement (from a rules perspective), can lead to gimmicks rather than genuine improvements to the sport.
Personally I think its boring simply because there really isn't any variety in strategy. I agree that iso basketball can be boring but that isn't really the same thing as having a viable midrange shot. The pick and roll and the drive and kick can all be used to create shots that aren't 3s or immediately under the basket, they just aren't because those shots aren't worth it. And I personally think the most boring playstyle in basketball is exemplified by Kyle Korver: a player who really does nothing but stand on the perimeter and run around screens until someone passes him the ball to shoot a 3.
Ultimately I guess I don't mind if some teams play like today's style of basketball, but I do mind if its the only viable strategy.
Arsenal bought an analytics company (more than one iirc), and did absolutely nothing with it. Man City are only just getting into the area. Liverpool have been doing it for a while (with fairly mixed success). There is almost no interest from management in applying analytics.
Additionally, sports are not equal. Baseball suits analytics. NBA is harder. And football is harder than the NBA (by a significant degree). All of this is measurable btw. One very simple point relating to this: there is no equilibrium strategy in football, it varies based on the opposition, teams that are bottom of the league can (under certain conditions) prevent a huge obstacle to the best team in the league.
Either way, it doesn't matter because almost no football teams are applying this knowledge (there are a few exceptions, some of the top teams are run by professional gamblers and they have been printing money from analytics for decades...so, in those cases, it is being applied).
The EPL has no salary cap, the obvious winning strategy is to buy the best players. Analytics in sports usually start with finding undervalued players which is the game that weaker teams are playing, not the teams you mentioned. Also, analytics in soccer has been around for a long time: https://fivethirtyeight.com/features/how-one-mans-bad-math-h...
It isn't. Again, football is not like American Football or the NBA where, for different reasons, you can buy one player and win it all. It is very possible to produce a winning team (although not one that will likely win the league) composed only of specialist players: Fulham (got to the Europa League final), Bolton, Stoke (first-time with Pulis), Leicester...these are just teams in the recent past in one league.
The vast majority of teams that try to "buy the best players" don't succeed (usually there is only one or two players currently in the game who can win games by themselves, there is a substantially larger group of players who cost essentially the same and don't perform at all) because they pay too much/buy players randomly who don't fit their system/overestimate skill.
I would look more closely at what I said. I did not say that analytics hasn't been around for a long time (for some reason, the article you link fails to mention that Reep actually worked for clubs, and found some degree of success...but there is no Nash strategy, Bolton got to the Europa League playing long ball football...it is a fine strategy suggesting that it doesn't work on average means nothing because everything is conditional in football).
Btw, your model of salary cap=pay most for players is obviously flawed if you consider that the non-existence of a salary cap does not occur in a vacuum. Player salaries/transfer fees are a dynamic competition so the lack of salary cap means that most players are overpriced (because clubs are inherently overoptimistic...there are clubs who make money just by developing players and selling them to bigger clubs). The actual implication of salary caps (in combination with FFP) is that success is correlated to your ability to generate revenue. It isn't that the top clubs can pay more for players, it is that they can "lose" more overpaying than anyone else. As an example, Manchester United have rock-solid sponsorship revenue (iirc, they even have a "tractor partner"...they sponsors for literally everything) so they can overpay for almost every player, lose tons of money doing so, and end up doing okay. If a club lower down the table made deals as bad, they would get relegated. No salary caps just mean the rich clubs get richer.
Your last paragraph is exactly why I bring up the salary cap. Your original thesis is “Football isn’t like American sports” and your “measure” is that is that there is no “equilibrium strategy”. Which you say without explaining what that means. It is after all a two player (two teams) zero sum game. You heavily imply that analytics are not applicable to football due to the properties of the sport itself. For all the reasons you outline in your last paragraph, many teams have ulterior goals other than actually maximizing win probability which is why analytics isn’t an emphasis. An analytics department would cost these farm teams additional money for example.
I am not saying that analytics cannot be applied. I have been making money applying analytics to football for years. But analytics is not some machine that you just cram data into and out come the best players. That may work with baseball it doesn't work with football because the nature of the game is totally different (another example is with NBA, NBA's scoring frequency and pitch size totally changes the dynamics...it is another invasion game, but one that has totally different properties to football).
No equilibrium strategy has been explained twice. If you don't know, I can't help you.
They aren't "farm teams". That only makes sense in the context of American sports (once again). Analytics is an emphasis at many of these clubs, it is how they win games (again, I am not sure if you understand that I am not talking about American sports...win probability is important because if you don't win games, you get relegated, and your club can stop existing in a few years...you need to win games).
You've claimed that there's no equilibrium several times, but as far as I can tell, you haven't explained it even once. Do you have a citation? Or do you have some model in which football fails to satisfy the criteria?
What I want to see happen is for a league to experiment with data driven rules that encode how the game should be played. For example, a dynamically altered 3-point value that ensures the expected value for different plays are equal. For example, some days, the 3-point will be worth 2.7 and other days 3.1 depending on league data. It would be awesome to see multiple strategies be optimal and reward teams that are good at multiple strategies as they can adjust their play style for whatever the data derived rules are.
I really want to see boxing scoring be fully automated. I would love to see crowdsourced classifiers of "good" boxing matches, rounds, and exchanges, compared with the traditional queensbury rules and hit scoring.
59 comments
[ 4.9 ms ] story [ 135 ms ] threadUsage of technology has ruined several aspects of traditional association football. The VAR for example, is ruining the serendipitous nature of football. Fans in general dislike the VAR because it removes this extra element of drama that the sport has.
I’m supportive of technology in sports though. I just think there should be a limit, otherwise they become a very boring and cold activity.
I’m not necessarily against the suggested approach here. Having analytics of how a game is going or went seems useful and a net positive. It’s just hard to tell if that could keep eroding those entertainment elements that make Football fun to watch.
Of course, but the reality is that analytics have proven that there are only really two shots worth taking in modern basketball: the 3 pointer and a shot near the rim. For anything in between the expected points for the shot is simply not worth it. Even an uncontested midrange shot is going to have similar or fewer expected points per shot than a contested 3-pointer or shot beneath the rim. And these two kinds of shots are spatially far from each other, so even if the opposing team knows this is your strategy, its still difficult to defend against. Teams and players that have tried to exploit the fact that modern basketball is fairly homogenous by taking relatively less defended midrange shots occasionally find streaks of success, but it hasn't proven sustainable, and certainly not enough to win a championship.
Basketball would probably benefit from either eliminating the 3 point shot, or, perhaps preferably, pushing the line back a few feet to even it out in terms of point expectations with midrange shots. Shots under the rim will still remain the most reliable point source, but teams won't have to divide as much attention on getting steam-rolled by three pointers. It will bring back scoring big men like a prime Shaq who have mostly disappeared from the game, still allow phenoms like Steph Curry to thrive (fewer players can match his ability to hit 3-pointers from further distance), and will make the midrange focused strategies more viable again.
The strategic trends always go in and out of fashion.
One thing that I see in Basketball that needs fixing though, is that the rules make the defender's job incredibly hard. Especially with the rules around fouls. They need to look into fixing that. I think a solution to that class of issues, will inadvertently fix the 3 pointer issues you cite too.
Yes, but by "inside the perimeter", you mean up-close to the basket. Zion is a great example. Take a look at his shot chart [0]. He doesn't even think about shooting more than a few feet away from the rim.
As I said, at this point, basketball has coalesced around offenses entirely focusing on shots at the rim, or beyond the 3-point line. Anything between there is a wasteland where teams don't even bother shooting anymore, despite Hall of Fame players like Michael Jordan and Karl Malone making those areas of the court a huge part of their game in the 90s. And this doesn't seem like much of a fad. Its a trend that has been becoming increasingly entrenched for nearly 2 decades at this point. The charts on this 538 article are all you need to see why this isn't simply a matter of what's fashionable, and is a simple mathematical reality under the current rules [1].
But I definitely agree with your last point. Basketball has numerous issues currently, of which unequal shot efficiency is only a part.
[0] https://www.statmuse.com/nba/ask/zion-williamson-shot-chart
[1] https://fivethirtyeight.com/features/how-mapping-shots-in-th...
the playoffs are all about effective shot selection, with the midrange becoming prominent because defenses tighten up arond the perimeter and the basket. lebron and anthony davis both explicitly featured their midrange game in last year's championship run. the clippers, incidentally, have the best midrange shooter (kawhi) and lost early last year because they relied too much on the 3-pointer. even the warriors of old used the midrange shot to keep defenses guessing enough to give their shooters space to shoot.
and that's exactly the issue with relying too heavily on analytics--humans aren't static, and pinning down the exact parameters where a model is valid is seductively elusive. mathematical models don't so much tell us about how the world is, but rather more about how the modeler sees the world. models aren't useless but they are limited (really knowing how is the hard part).
[1] - https://nbasavant.com/player.php?ddlYear=&ddlShotMade=&ddlTe...
In contrast, fans have been fine with the goal-line technology, which gives decisive (usually) and quick results.
The use of AI in this paper seems more relevant for setting team strategies and picking players rather than enforcing rulings.
For example, in basketball, it should be able to do goal-tending in near real time. Also 3s in the key.
The holy grail though is if it can help charge/block calls. Or we should consider changing the rule so that it can be consistently called, but that's a topic for a basketball forum.
Love that quote.
I agree that those sports have suffered in terms of watch-ability at the hands of maximizing competitive efficiency. But I don't really know why anyone would expect anything different. The point of the game from a team/player perspective is to win. Using analytics to determine that there are advantages to three-point shots or walks isn't any different than any other strategic layer of the game. The solution shouldn't be to rail against analytics (which is no solution at all), it should be for the leagues to use analytics of their own to control for some of these strategies, like a government is supposed to hedge against externalities in an market. For basketball, simply push the 3-point line back a few feet so its no longer so much more advantageous than a midrange jump shot. I'm not much of a baseball fan, but surely the league can do something, like increases the number of balls to walk to 5, that might bring some of the boring-but-efficient strategies into line with more exciting ones.
Though I suspect the author and many others would be against any substantial rule alterations given their abhorrence towards change, and would rather just pine about the good old days.
My personal interest is for soccer to allow more substitutions to let coaches tweak the team more as the game is played. Small change; maybe big results in scoring.
All of what has been mentioned has been conceived of, thought about and discussed before, and some years ago. I've seen more advanced thinking in some models used to make bets on football matches.
As a Man City fan, I'll try and make this sound less snarky than it will come across, but it's going to be snarky: it's good to see Liverpool are finally - with Deep Mind's help - catching up to where many other teams in the league were more than half a decade ago.
Most players and coaches are not particularly interested in these models and the most useful applications seem to be related to scouting and the transfer market - "I need a replacement for player X, but 10 years younger and with a better left foot", is the sort of problem that data science is already helping with - and the clubs themselves prefer to put their money onto the field of play rather than expensive and experimental ML training, so the market for this sort of work is limited.
The challenges in this field are not really about data, algorithms or computational capability of the hardware.
The main issues are of applicability, cultural fit and economics.
Finding methods for addressing _those_ issues might be more useful to mainstream AI adoption than the data, algorithm and hardware problems many seem to look at first.
Your point about applicability is totally right though, see Arsenal with StatDNA and the arguably weak impact of Barcelona’s Innovation Hub. I’d argue that Leicester’s use of (at the time) very rudimentary stats, nevertheless well integrated into their process, was a big part of their sudden success.
[0]: https://www.liebertpub.com/doi/pdf/10.1089/big.2014.0018
There are still areas where analytics will continue to be important in sports and player assessment/team composition will always heavily rely on it. However the next steps for sports analytics in my mind are things that go on behind the scenes of the sport: personal training routines for players, managing wear and tear and predicting injuries, etc.
Also, the leagues themselves have lots of room to improve their products with analytics. Many complaints have been raised (which I agree with) about how boring modern basketball/baseball has become due to analytics causing teams to converge on strategies that maximize efficiency but are also quite boring. It isn't on the players/coaches to try something more exciting at the expense of winning. It's the league's job to make the product interesting. Analytics can be part of the solution, like determining that by pushing the 3-point line out several feet, the value of the shot is brought in line with other options that simply aren't viable right now.
Obviously the games are different, but perhaps there are some common themes or generalized structures that can help frame what questions to ask?
So, from what little I know of LoL, you’re simultaneously trying to attack the enemy base and protect your own. Presumably there are interesting second order things to study here - how can you get close to the base, how can you destroy it quicker than the opponent destroys yours etc. I assume if there are any epiphanies along the lines of “shoot threes” in basketball or “shoot closer to goal” in football, they’re probably well trodden.
Much of the game is presumably controlling the space between, trying to create overloads against opposition players, and not be overloaded yourself. The best teams in football are experts at using space, and at manipulating their opponent’s shape to create gaps or opportunities for ambushes. So an interesting thing to study would be teams tendencies to overextend - what sort of structures appear to offer them opportunities, but actually keep your players close enough together to pounce on them. The ghosting work mentioned in the article would be interesting here, as would work on pitch control:
https://www.researchgate.net/profile/William-Spearman/public...
I'd also imagine any data you can crunch from solo queue games is of limited use in competitive play.
The easily digestible stats like KDA or gold/min are relatively useless in this regard which is what I meant by them being low hanging fruit.
So I’m currently in a situation where I’m curious on how to best quantify or develop a series of metrics that can prepare teams for their opponents. The current system of watching vods, taking notes, and making slides is rather dull if I’m being honest...and really not paradigm shifting. If you’re interested I can show you videos/presentations/figures.
> Obviously the games are different, but perhaps there are some common themes or generalized structures that can help frame what questions to ask?
One of the most important things to understand is what the front office, coaches, and players want to know. Like I said, much of analytics these days (and not just in sports) is a solution searching for a problem. We build models based on what we can with the data, but the output of the models isn't actionable or something anyone is asking for. A better approach is to start from the questions that loom big in the eyes of those you are doing the analytics for. That sounds simple, but often doesn't happen, either because communication is poor, or neither party really understands what the other is trying to do. Also, often times a team doesn't even really know what questions they'd like answered, or at least not enough to verbalize it well.
One thing I've found consistently useful is focusing on measuring uncertainty. These days people are extremely excited about machine learning and "AI", and I work extensively with deep learning in my current position. But most times in analytics, especially sports analytics, simply getting the best prediction possible isn't actually useful. What is far more useful is measures of uncertainty through more traditional statistical methods, especially Bayesian statistics and Monte Carlo simulation. It's one thing to predict a player in the draft will be better than another. But a team usually knows the answer to that already anyways. Its far more useful to quantify the range of possible outcomes for a player. Is it practically a sure thing? Is it not a sure thing but a reasonable bet? Or is it really a toss-up? These are insights that teams often don't have but can find much more useful in their decision-making.
I generally don't focus on in-game strategy, since it is harder to give the team something they don't already know that they can reasonably act on. But meta-game insights could have a lot of potential. For traditional sports, this can be things like assessing player value, injury risk, draft capital, and contract valuation. Some of these may not translate well to LoL. I haven't played the game, but I've watched it a few times, and perhaps something could be done looking for insights regarding the hero pool. There are so many different heroes in the game that can act/oppose each other that quantifying those relationships somehow could be interesting.
I'd be super interested in that and seems like the more data we can collect from watches etc the more potential variables to model or train ML suggestions on?
lots of companies spending big money on this market too. Apple, pton, smart watches.
The documentary Breaking2 from nike about the marathon is really good, shows some advanced individual measurements that wouldn't be available to almost everyone (lactic acid blood draws while running..). in my sport climbing finding new ways to push lactic acid tolerance or better improving physiology through BFR or whatever training would be really valuable and maybe push the sport even further.
But basketball seems the opposite to me. Analytics has shown that except in a few superstar cases, back to the basket isolation mid range jumpers while the rest of the team stands around and does nothing (IMO the most boring play in basektball), is a terrible play call.
Analytics has shown that the pick and roll is a fantastic play in terms of points expectancy and I find it to be a really enjoyable play to watch because it often results in dunks and nifty passes or acrobatic layup attempts.
Analytics has shown that faster pace, shooting earlier in the shot clock, and getting out in transition more often to be hugely valuable strategies, all strategies that I think are more enjoyable to watch.
The perceived value of 3-pointer shooting has caused offenses to spread the floor creating more driving lines and making it harder for defenses to pack the paint which has created more offense which I think most people enjoy seeing.
I'd love to hear what you think analytics has done to make modern basketball more boring.
Analytics only uncovered these structural issues for teams to exploit. Personally, I think if the strikeout rate were tamed back to 1990s levels, the game would balance.
The optimal strategy for both sides is for pitchers to go for the K (increases K rate) and for hitters to try and hit the homerun (also increases the K rate).
Basketball is time-limited, and therefore the strategy of maximizing the number of shots within that time period as well as maximizing their value, make sense.
I'll note that I don't necessarily think one is better than the other, as each game can have a different approach. I also think that maximizing purely for excitement (from a rules perspective), can lead to gimmicks rather than genuine improvements to the sport.
Ultimately I guess I don't mind if some teams play like today's style of basketball, but I do mind if its the only viable strategy.
Arsenal bought an analytics company (more than one iirc), and did absolutely nothing with it. Man City are only just getting into the area. Liverpool have been doing it for a while (with fairly mixed success). There is almost no interest from management in applying analytics.
Additionally, sports are not equal. Baseball suits analytics. NBA is harder. And football is harder than the NBA (by a significant degree). All of this is measurable btw. One very simple point relating to this: there is no equilibrium strategy in football, it varies based on the opposition, teams that are bottom of the league can (under certain conditions) prevent a huge obstacle to the best team in the league.
Either way, it doesn't matter because almost no football teams are applying this knowledge (there are a few exceptions, some of the top teams are run by professional gamblers and they have been printing money from analytics for decades...so, in those cases, it is being applied).
The vast majority of teams that try to "buy the best players" don't succeed (usually there is only one or two players currently in the game who can win games by themselves, there is a substantially larger group of players who cost essentially the same and don't perform at all) because they pay too much/buy players randomly who don't fit their system/overestimate skill.
I would look more closely at what I said. I did not say that analytics hasn't been around for a long time (for some reason, the article you link fails to mention that Reep actually worked for clubs, and found some degree of success...but there is no Nash strategy, Bolton got to the Europa League playing long ball football...it is a fine strategy suggesting that it doesn't work on average means nothing because everything is conditional in football).
Btw, your model of salary cap=pay most for players is obviously flawed if you consider that the non-existence of a salary cap does not occur in a vacuum. Player salaries/transfer fees are a dynamic competition so the lack of salary cap means that most players are overpriced (because clubs are inherently overoptimistic...there are clubs who make money just by developing players and selling them to bigger clubs). The actual implication of salary caps (in combination with FFP) is that success is correlated to your ability to generate revenue. It isn't that the top clubs can pay more for players, it is that they can "lose" more overpaying than anyone else. As an example, Manchester United have rock-solid sponsorship revenue (iirc, they even have a "tractor partner"...they sponsors for literally everything) so they can overpay for almost every player, lose tons of money doing so, and end up doing okay. If a club lower down the table made deals as bad, they would get relegated. No salary caps just mean the rich clubs get richer.
No equilibrium strategy has been explained twice. If you don't know, I can't help you.
They aren't "farm teams". That only makes sense in the context of American sports (once again). Analytics is an emphasis at many of these clubs, it is how they win games (again, I am not sure if you understand that I am not talking about American sports...win probability is important because if you don't win games, you get relegated, and your club can stop existing in a few years...you need to win games).