[HN Gopher] Advancing Sports Analytics Through AI Research
       ___________________________________________________________________
        
       Advancing Sports Analytics Through AI Research
        
       Author : atg_abhishek
       Score  : 62 points
       Date   : 2021-05-09 09:35 UTC (1 days ago)
        
 (HTM) web link (deepmind.com)
 (TXT) w3m dump (deepmind.com)
        
       | dovrce wrote:
       | Technology makes sports less interesting, refinement culture
       | https://paulskallas.substack.com/p/refinement-culture
        
         | bart_spoon wrote:
         | 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.
        
           | JALTU wrote:
           | +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.
        
       | whoisjuan wrote:
       | 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.
        
         | jgalt212 wrote:
         | 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.
        
         | rjtavares wrote:
         | 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).
        
           | clairity wrote:
           | 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.
        
             | bart_spoon wrote:
             | > the 3-pointer by itself isn't point-maximizing
             | 
             | 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.
        
               | dynamite-ready wrote:
               | 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.
        
               | bart_spoon wrote:
               | > 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.
               | 
               | [0] https://www.statmuse.com/nba/ask/zion-williamson-
               | shot-chart
               | 
               | [1] https://fivethirtyeight.com/features/how-mapping-
               | shots-in-th...
        
               | clairity wrote:
               | 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).
        
               | hervature wrote:
               | 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.
               | 
               | [1] - https://nbasavant.com/player.php?ddlYear=&ddlShotMa
               | de=&ddlTe...
        
               | clairity wrote:
               | 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.
        
             | rjtavares wrote:
             | 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).
        
               | kenjackson wrote:
               | In football it is the forward pass.
        
               | jghn wrote:
               | football in this context means association football, aka
               | soccer
        
         | daveevad wrote:
         | 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.
        
         | LetThereBeLight wrote:
         | 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.
        
           | kenjackson wrote:
           | 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.
        
       | rjtavares wrote:
       | > 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."
       | 
       | Love that quote.
        
       | slg wrote:
       | 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.
        
         | thom wrote:
         | 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.
        
       | jvanderbot wrote:
       | 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.
        
       | bart_spoon wrote:
       | 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.
        
         | stanford_labrat wrote:
         | 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?
        
           | thom wrote:
           | 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:
           | 
           | https://www.researchgate.net/profile/William-
           | Spearman/public...
        
             | colinmhayes wrote:
             | 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.
        
           | amch wrote:
           | 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.
        
         | hogFeast wrote:
         | Football isn't like American sports.
         | 
         | 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).
        
           | hervature wrote:
           | 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...
        
             | hogFeast wrote:
             | 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.
        
               | hervature wrote:
               | 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.
        
         | dillondoyle wrote:
         | 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.
        
         | lprubin wrote:
         | 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.
        
           | polygotdomain wrote:
           | 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.
        
           | edmundsauto wrote:
           | 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.
        
             | lprubin wrote:
             | 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.
        
               | edmundsauto wrote:
               | 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.
        
               | arrosenberg wrote:
               | They also keep messing with the damn ball, which this
               | year has the league hitting about .230 because more fly
               | balls are falling inside the park.
        
               | edmundsauto wrote:
               | 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).
        
         | hervature wrote:
         | 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.
        
       | PaulRobinson wrote:
       | 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.
        
         | wdb wrote:
         | 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.
        
           | PaulRobinson wrote:
           | On health tracking stuff, rugby was some years ahead of any
           | other sport - is that still the case?
        
         | thom wrote:
         | 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.
        
           | PaulRobinson wrote:
           | 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.
        
             | thom wrote:
             | 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.
        
           | hogFeast wrote:
           | The Andy Carrol purchase? Liverpool's process clearly
           | developed over time.
        
             | thom wrote:
             | That was a Damien Comolli thing. Arguably a stats driven
             | purchase though so a cautionary tale for all.
        
         | theja wrote:
         | 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].
         | 
         | [0]: https://www.liebertpub.com/doi/pdf/10.1089/big.2014.0018
        
       | wdb wrote:
       | Interesting years ago worked on using AI and body sensors to
       | determine the health and the chance of concussions in football
       | players. Awesome project.
        
       ___________________________________________________________________
       (page generated 2021-05-10 23:01 UTC)