[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)