You've spent a small fortune on the squad, got state-of-the-art facilities and employ a dietician and a psychologist - but today you'll win nothing without an analytics team to crunch the numbers from every aspect of your players' performances. We do the maths so you don't have to...
Category
🥇
SportsTranscript
00:00Clubs at every level of the football pyramid are becoming smarter and more efficient.
00:13How? The use of data.
00:16To hell with conventional wisdom. The way we've been doing it, it's not been working.
00:21Analysts are now recording data from thousands of actions during games and training sessions
00:26to help shape pre-match preparation and post-game debriefs,
00:30pinpoint transfer targets and develop young talent.
00:33The genie is out of the bottle, I don't think it's going back in.
00:35We may know more about the opposition than they actually know about themselves.
00:40The growing use of analytics in football has attracted criticism and cynicism.
00:44These are athletes, they're not spreadsheets.
00:48Battle lines have been drawn between the analysts and the traditionalists.
00:53Can football be translated into numbers by data bots?
00:56Or does it require special insight from real football men?
01:11In 2002, one of the most unfashionable teams in Major League Baseball, the Auckland Athletics,
01:17defied the odds to go on a record-breaking 20-game winning streak.
01:22Their success was powered by a new approach to player recruitment, sabermetrics.
01:28Well it started, I'd played for 10 years professionally,
01:31and so when I stopped playing I entered the front office and I started reading this stuff.
01:35Again, the baseball academics, it made sense to me.
01:38And I had my own experience with which to look at both sides.
01:42I came from a traditional baseball background as a player,
01:44and I was reading this new stuff that sort of put player performance in order for me.
01:50It was very rational.
01:52I could see why a baseball team was good.
01:55You could look at numbers and explain why they were good,
01:57instead of sort of looking at things anecdotally
01:59and trying to use non-quantifiable reasons to apply success.
02:07We were one of the smallest teams in the league, we were actually losing money.
02:10But it also created a great platform.
02:13It meant that if we just did things the same way the New York Yankees,
02:17a.k.a. the Manchester United did,
02:19we were destined to finish where our player wages said we should.
02:23If you had the lowest payroll, you were probably going to finish in last.
02:27So we had the opportunity, because we had nothing to lose,
02:30to implement something differently.
02:32The success of the Auckland A's encouraged sports teams around the world
02:35to replicate the model pioneered by Billy Bean.
02:39Early adopters believed the moneyball approach
02:41could give them an advantage over their competitors.
02:44We knew it worked on individual players,
02:46and we were able to apply it to the whole team.
02:49We won four division titles.
02:51Three division titles in a wildcard
02:53averaged almost close to 96, 97 wins per year.
02:58So we had immediate success.
03:00But the biggest thing, the most important thing,
03:02is we understood why we were successful,
03:05and we understood where we went wrong.
03:07I mean, the numbers would show us.
03:09Billy Bean had the huge luxury of not looking at relegation.
03:13If you don't have to look at relegation, you can try all kinds of stuff.
03:16Analytics and big data are driving the strategies
03:19of major corporations around the world.
03:21And these methods are now filtering into football,
03:24from the boardroom to the boot room.
03:27Football clubs over the last 10, 15 years
03:29have had to deal with a technological revolution.
03:32What that's meant is they've now started to collect,
03:35through third-party vendors, lots and lots of data on football.
03:39And that those data primarily originally were collected
03:42for fans and for media outlets to use.
03:44They've made their way into the clubs themselves,
03:47and now you have football departments that have to contend
03:50with what's kind of an avalanche of information.
03:53Sports data is basically a reconstruction of the match.
03:56Okay, so why do we collect data?
03:58It's basically so we can tell a story of how the match is played.
04:01And so you can look through it in various lenses.
04:04So you could have just event data in how many passes and shots.
04:07But as we know, football, it's not a great reconstruction.
04:10But if we have the tracking data,
04:12so if you can see the dots run around,
04:14we can basically reconstruct the game in a better way.
04:18It's like having a scout at every game.
04:21And not just having a scout at every game,
04:24because we're collecting data on everything
04:26that the player is doing on the field.
04:28It's like having a scout for every player in every game,
04:31because everything they do is recorded.
04:33Now it's not so much about collecting the data,
04:36it's making sense of that data.
04:38The stakes are high at the top of the footballing pyramid,
04:41but lower down, one bad season can have catastrophic repercussions.
04:45Small clubs with limited budgets can't afford to make a mistake.
04:49To reduce the risk of acquiring a dud signing,
04:52they're turning to Bean's sophisticated sabermetric approach.
04:56So I like to try and get to the training ground as often as I can
04:59and help out with the guys down there.
05:01But a lot of the time I'm based here in Ecotristi,
05:04with a full-screen set-up.
05:06I'm surrounded by a lot of energy traders,
05:08and at times there's millions of pounds deals getting made,
05:11and I'm sat here watching League 2 football and providing analysis.
05:14So it's a pretty unusual workplace,
05:16and probably quite different to a lot of analysts in the Football League,
05:19but it's good.
05:20So here at Ecotristi I'm the Chief Operating Officer.
05:23In energy trading we buy and sell energy, mostly buy,
05:26to meet the needs of our customers on a day-to-day basis.
05:29We're able to take a lot of the skills and the data analysis
05:32that we undertake in the trading front of energy into the world of football.
05:37So we saw it as an opportunity to be creative in the data and analytical space,
05:42and see if we can form a competitive advantage at a lower level.
05:48It wasn't really necessarily about budgets,
05:50but it was about trying to maximise what we can get
05:53out of every single player that we recruit,
05:56trying to bring together a list of players that is the best
06:00from the manager's eye and augmenting that with the data,
06:03and also performance-wise,
06:05we just wanted to understand all aspects of our performance.
06:08So it's essentially doing the same thing in business
06:11and taking that into the world of football.
06:14The Billy Bean story is really originally a story about player recruitment
06:17and finding inefficiencies in the market
06:20on the back of going against conventional wisdom, really.
06:24They use data to try and scout players,
06:27try to find players that no one else wanted,
06:30that were able to do things that would help the team win.
06:34Manchester United and Burnley are very different clubs
06:36despite the fact that they play in the same league,
06:38and as a result, Burnley has to take a very different approach
06:41to putting together a team than Manchester United.
06:44There's a lot of money being spent,
06:46but for more the mid-level clubs, there should be bargains available.
06:50So if they're smart with the data,
06:52and if they look through it with a certain lens,
06:54they could be able to find some gems out there.
06:59Yeah, this is where all your goals come from.
07:02A lot of them are in the six-yard box.
07:04We get the ball to you in there.
07:06That's my bread and butter, yeah.
07:08The recruitment side for a small club, like you say, is really, really key,
07:11and it's important that we're different.
07:13In January, every club will be after the same players,
07:16and probably we can't compete for those players that everyone's after,
07:20so we have to find other types of players,
07:22and we have a different way of playing,
07:24and we have to find players that can fit into that,
07:26and we have to use the data for that.
07:28Yeah, I think the one I would definitely pick out is Christian Deutsch.
07:31He's been our top scorer last year.
07:34He's our top scorer this year.
07:36I think he's second or third highest goal scorer
07:39in the top six English leagues in 2017.
07:42Yeah, I think Christian's done better than we envisaged,
07:47but we knew that the basics were there.
07:49We knew he could score goals.
07:51We knew he got in the right positions on the pitch
07:53because his data showed that,
07:55and it was then a case of us trying to work with him
07:57how to convert those chances from the positions he got into,
08:02which his data showed.
08:03So that one is proof of the data works.
08:06I mean, the value for money on that one.
08:08Today we paid £30,000 for him,
08:10and he's worth an awful lot more than that now.
08:13Tom, who looks after the data,
08:16I'll give him a list of targets,
08:18and he'll go through them and give us graphs
08:20in terms of their value and what they're good at,
08:23what they're not good at, what their metrics are
08:25in terms of if it's a striker, goals, expected goals.
08:29As analytics evolves, new metrics arrive,
08:31and some are more widely accepted than others.
08:34Expected goals is one example of such a seemingly divisive tool.
08:38So what exactly does it mean?
08:41It's a measuring tool of the probability of that shot
08:44from that specific location and resulting in a goal.
08:47So we look at thousands of different shots
08:50that occurred in League 1, League 2 and National League,
08:52so we make it relevant to our level of football.
08:54We'll then apply where it was on the pitch,
08:58the angle, the distance, was it a headed shot,
09:00was it a shot with the feet, how was it assisted?
09:03Put all those things into a algorithm.
09:06That will then produce a number which will tell us
09:08how likely that is to result in a goal.
09:10If the expected goal is 0.15, 15% of the time,
09:13a shot from that location will result in a goal.
09:16It makes me feel a lot better about myself
09:19because my expected goals are a lot less
09:22than what I'm achieving at the moment,
09:24so that's good for me.
09:26I just think football's changing,
09:28and any little inch you can get, it helps out massively.
09:33It might be the difference at the end of the season
09:35between getting promoted or relegated.
09:38I had nine games without a goal this season,
09:41and the manager pulled me and said,
09:44I know we're having bad results at the moment,
09:47but I don't want you to try and get involved
09:49and do stuff which you're not as good at.
09:51He said, you're best when you're in the box
09:53and you stay the width of the goals.
09:55That's where you score your goals, and I've done that,
09:57and I've gone on a little bit of a goal-scoring run,
09:59so that's where the stats have helped me and the manager.
10:02It tells me where to run and what positions
10:04I should get myself into to help my game
10:06as much as possible and the team.
10:09Competing against the Premier League's mega-rich
10:11requires creative thinking.
10:13To punch above their economic weight,
10:15Southampton created the Black Box,
10:18a live database collecting player metrics
10:20from every major league.
10:22This has enabled them to acquire players
10:24of undervalued talent and sell them on for a profit.
10:27Sadio Mane, Dejan Lovren, Morgan Schneiderlin,
10:30Victor Wan-Yama, the list goes on.
10:34A lot of the KPIs that we look for the different positions
10:37is something else that's been consistent for quite a while,
10:40so a lot of the scouts know the type of players
10:42that we're looking for at the football club,
10:44so they'll already be creating scout reports
10:47for any players that they've seen up there,
10:49so they can recommend them to put on our target list
10:51and someone that we need to look at
10:53as a potential sign-in for the football club,
10:55but we'll also use the data on a global scale
10:58to highlight any top performers,
11:00and from that will be an area that we need to provide
11:04some more scouting information on,
11:07so that will be from the eye, from our scouts.
11:10Yes, there are some players that will have been signed
11:13because their stats look good.
11:14Payet at West Ham is a good example.
11:16Gabriel at Arsenal was a good example of that kind of an approach,
11:20but that's really kind of missing the point.
11:22The point of analytics is doing things differently.
11:25One of the reasons for these crazy prices
11:27that we're paying for players these days
11:29is that people get really wedded to one player.
11:32They really get, they think that this is the guy,
11:34we need to have him, and we're willing to pay over the odds.
11:38What data can help you do is generate options.
11:41Maybe find guys that are kind of like that other guy,
11:44or maybe who would fit into the team in a slightly different way,
11:47and it allows you to walk away from a bad deal.
11:50It allows you to walk away from a really expensive deal.
11:53Football has actually been collected the most data for the longest time,
11:57but football is the most complex sport,
12:00so it's low-scoring, it's continuous, it's time-varying.
12:04It's very strategic, OK? It's very subjective.
12:07So just say you and I were analysing a game,
12:10we could come up with different opinions.
12:12When you compare it to other sports like basketball, it's high-scoring.
12:16Tennis and American football, they're segmented.
12:18Baseball, it's segmented.
12:20You know, it's very easy to do the analysis.
12:22You have a lot of data points.
12:24So the key for football is actually to come up with the right language
12:28and ask the right question for specific things.
12:31How was our formation?
12:33How did we press?
12:35How were we on set pieces?
12:37Did we attack by the counter-attack?
12:39All these different things we have to learn directly from data.
12:44When I played, it was a video recorder,
12:47and looking at the game back now,
12:50we monitor them every day in terms of their sleep, their training.
12:56Everything they do, really, is massive.
12:59We may know more about the opposition
13:01than they actually know about themselves.
13:03Yeah, I think a coach's eye can see a certain amount.
13:06What the data does is just back that up.
13:08We can look at data of the team we're about to play,
13:11and we can break down strengths and weaknesses of the team that we're playing.
13:15There was a game a few weeks ago,
13:17a game that we actually went on to win.
13:19In my opponent report, I noticed that the team played pretty deep.
13:22Their average position was quite deep,
13:24and their pressing metrics weren't very high,
13:26so they allowed you a lot of time on the ball.
13:28I suggested that we'd be able to play a lot of football,
13:30and we did.
13:31We sort of passed them to death, really.
13:33I'd also highlighted an area where they were weak,
13:35and they conceded a lot of shots.
13:37I said, if we can get our key players in these areas,
13:39there's a fair chance we can score from here,
13:41and we actually scored our first goal in exactly that area.
13:46Data in terms of pre-match, a lot of it is video-based,
13:49but in terms of statistical data,
13:52it's used, I guess, to look at trends,
13:54so it won't be just from one game.
13:56We'll look from game to game
13:58and build up a database to create a performance profile on that team
14:02and look at any individuals that are maybe performing to a higher level.
14:09The black box also helps Southampton develop home-grown talent
14:12they can sell for huge profit.
14:14Data helps to drive player recruitment at academy level
14:17and to maximise the potential of their scholars.
14:20I started training when I was eight,
14:22and then finally signed at nine, so quite a young age.
14:26I think when we first got here, it was just a load of numbers on a sheet,
14:29but now we understand what it actually is, the details of it,
14:32and where we can improve and what we need to look at.
14:35It's helped me massively.
14:37I think when I first got here, I didn't really know what to do.
14:40Just watching the game, I wasn't really taking notice,
14:43but as I started to learn more,
14:45I think I focused on myself more and the positioning I'm taking up
14:48and all the little details you can sort of figure out
14:51what you have to do to be better,
14:53and so it's helped me massively develop.
14:58A founding principle of this organisation is youth development.
15:03It's everything we stand for, excellence, potential, it's a strapline,
15:06it's everything we work towards,
15:08and even when you buy a senior player, first-team player,
15:10still the principle is the same.
15:12Can we improve him? Because we may be selling him,
15:15and if we are selling him, we need to be selling him for a profit,
15:18so it's all about improving that individual.
15:23It was never really the dream to produce a player to sell.
15:26It became the business model
15:28when first-team started sliding through the leagues
15:31and ultimately into administration.
15:33It was selling of players, Theo Walcott and Alex Oxlade-Chamberlain
15:38and Gareth Bale.
15:40We all, as fans and also as a staff member here,
15:42we all dream of, what happens if we kept hold of those players?
15:45What would he have done?
15:46But the reality, if we kept hold of those players,
15:48we would have gone out of business.
15:50There's a huge amount of data that's collected around the players,
15:54from match day data to the way they sleep
15:57to the way they're feeling in the morning
15:59to training their power outputs in the gym.
16:02The challenge is, what do we do with that data
16:05and how important is it, the analytics around that data?
16:09So on a daily basis, we collect information from players
16:12from GPS units, so we would look at distances covered,
16:15the speeds at which they're covered,
16:17and other information such as accelerations and decelerations,
16:21and we would use that in a more individualised approach
16:24so we can optimally adjust their training programmes
16:28to make sure that they're fresh and they're in peak condition come match day.
16:34We're now in an amazing position where, for the first time,
16:37we're able to turn down those opportunities to sell players
16:40and push back against the big clubs
16:43and turn around and say, no, not for sale.
16:48Yeah, it's a huge point of the game now.
16:50Obviously there's a lot of other sports that use data or heavy analytics.
16:54Soccer has not yet cracked, I don't think, the code yet
16:57in terms of what are the key indicators
17:00of what's going to make a player successful or not.
17:02I think there's several companies out there that aggregate the data
17:06and try to make it easier for you to make a decision.
17:09But at the end of the day, I think soccer people want to still see the player
17:13and see how that marries up with the data
17:16that you're seeing because sometimes the data doesn't always match
17:19what you're seeing on the field because of the free-flowingness of the game
17:23and the fluidity of the sport.
17:25Yeah, I think the mentality of a player, I think that sometimes the soccer IQ,
17:30and you're only going to get that from seeing sometimes live,
17:33obviously video as well, but also sitting down with that player
17:36and having a conversation with them about the game itself,
17:39about his particular skill set, about your own club's philosophy on the game
17:45and see if there's a match there.
17:47And you can't get answers from that with data.
17:52Analytics has come a long way from past completion rates and heat maps.
17:56Some of the brightest minds in the game want to find an algorithm
17:59to calculate the most valuable intangibles, like team chemistry.
18:04What will this mean for the future of football?
18:07You know, all goals aren't created equal,
18:09and the ability to weight the difficulty of those goals,
18:12the player with the skill set to do those things,
18:14should be rewarded as opposed to a guy who maybe just tapped the one in
18:19because Suarez drew three defenders on him, penetrating,
18:22and he flipped it off to him, and the other guy just taps it in.
18:25Well, the goal gets paid for in today's world.
18:28But shouldn't the guy who created all those things
18:30and measuring those things is really the challenge,
18:32and giving proper credit to player performance
18:34is what we're all trying to achieve, not just in baseball,
18:36but in every sport, just like in business.
18:39So there's lots of cool stuff that people haven't thought about.
18:43So the idea of ghosting,
18:45be able to simulate plays that you haven't seen before.
18:50So you can have an example of a play, and you can say,
18:52well, how does this team defend in that situation?
18:55What happens if I switch that player with another player?
18:58How does the outcome change in terms of just body shape?
19:01Okay, where's the player facing?
19:03Are they making the right decisions?
19:05In terms of injury analytics, player load, fatigue,
19:08how's their technique changing over time?
19:10Now, using deep neural networks, we can actually simulate these things.
19:14I think in terms of injury prediction,
19:17I think you'll find there'll be less injuries.
19:19So there'll be less soft tissue injuries.
19:21You're still going to have the edge cases,
19:23but soft tissue injuries, I think they'll be minimized.
19:27I think in terms of player valuation, in terms of performance,
19:31I think that'll be normalized.
19:32I think you see the volatility now.
19:34It's because we haven't got these good metrics.
19:37However, what you don't take into consideration is the media.
19:40Okay, the media and the shirt sales.
19:42There's all these other things that need to be taken into account.
19:49You're never, I guess, going to have data
19:51just making a sole decision, I think, in anything.
19:53But as data advances,
19:55and the individuals that are part of that process,
19:58and they're creating and maximizing the use of data
20:02in clubs and in different sports,
20:04I think those people are more crucial in the process.
20:08And I think data becomes more important
20:11in what we do from day to day.
20:15We have to communicate with domain experts.
20:18And if we can't speak their language,
20:20then we're basically not going to be like them.
20:22It's an exciting area to be in,
20:23because it's constantly evolving and improving.
20:25As technology improves.
20:27The genie is out of the bottle, and I think it's going back in.
20:31When you've got open-minded people, it works really well.
20:34Hopefully it can tell us if we're going to win or lose.
20:37If the data can tell me we're going to get three points on a Saturday,
20:40it'd save me an awful lot of work.