Moneyball’s recruitment has paid off for Liverpool Football Club, but will it replace the good old talent scout?
Shortly after the Fenway Sports Group (FSG) purchased the Boston Red Sox Major League Baseball (MLB) franchise in 2002, FSG co-founder John W Henry asked Billy Beane to take over as Red Sox general manager. to take.
Beane, general manager of the Oakland Athletics, had revolutionized player recruitment in the MLB using performance metrics to find quality players who were undervalued in the MLB draw.
This allowed the ‘As’ to compete with wealthier franchises. Beane turned down the Red Sox job, stayed in Oakland and has since been promoted to executive vice president.
The best-selling book, “Moneyball,” which became a Hollywood movie, told the story of Beane (Beane was played by Brad Pitt). In 2010, FSG bought Liverpool Football Club.
Two years later, they hired Ian Graham, a physics graduate from Cambridge University, to set up their own data research unit in Liverpool.
Part of Graham’s brief was to use live player tracking data to locate and analyze players that fit the club’s playing needs and budget. Liverpool, like the Oakland Ashes, went up against richer rivals – Chelsea and the two Manchester clubs at home.
And in Europe like Barcelona, Real Madrid and Paris St Germain. Back then, some clubs used data to find new players.
But in general, player recruiting was still the domain of scouts – experienced professionals with a keen eye for a player, who would watch transfer targets live and on video.
Things didn’t go well for Liverpool. Andy Carroll, Mario Balotelli and Christian Benteke were expensive flops.
Borini, Markovic, Sakho and others were brought in without much impact. But in the background things started to change. In 2015, manager Brendan Rogers, unimpressed by the data-driven commission approach to transfers, was replaced by Jürgen Klopp.
Klopp had run Borussia Dortmund, a club with a similar business model. To compete with Bayern Munich, Dortmund had to find cheap talent with the potential to become world class, rather than ready-made stars.
Klopp also had a specific, established style of play that he fully believed in and would not doubt. Klopp’s fast-paced attacking approach had already been successful at Dortmund, where he won two German league titles and reached a Champions League final.
At Liverpool he just needed the right players. That was a challenge that Ian Graham and his team of analysts were able to tackle. Sadio Mané, Mo Salah, attackers with an explosive pace and a lot of energy came in.
The club recruited Georginio Wijnaldum and Fabinho, solid hardworking midfielders to shield the defense and protect against counter-attacks. Virgil van Dijk and goalkeeper Alisson were bought to improve the defence.
In the last five years, Liverpool have spent a net amount of £108.2 million (difference between players bought and sold), winning the Premier League, the Champions League and reaching another Champions League final.
At the same time, Manchester United spent £484.88 million nett without winning the title, while Manchester City invested £601.98 million and won the title four times. In the Covid-hit 2020 transfer window, Chelsea spent £222.48 million on new players.
Big names have come and gone with all three of Liverpool’s biggest domestic rivals without making much of an impact. Other signings are still there, but have underperformed.
Think Kepa, Morata and Bakayoko at Chelsea; Cancelo, Rodri, Stones and Danilo at City; Lukaku, Sanchez, Fred, Maguire and Pogba at Manchester United. No doubt some of these players – Stones, Maguire and Pogba, for example – have gone a certain way recently to justify their transfer fee.
However, the list of expensive transfer mistakes is actually a lot longer, especially at United. Last year, the Old Trafford outfit bought an attacking midfielder, Donny van de Beek, for £35 million, who has played just 19 league games.
This is mainly because United had already spent £200m on attacking midfielders, including Bruno Fernandes who was only bought for £49m last January.
Mistakes are made when assuming a new player will replicate stats from his previous club,” said Dr Bill Gerrard of the University of Leeds. Gerrard is known for applying the Moneyball model to football.
He has worked with Billy Beane worked on a system to evaluate footballers, and is currently an advisor analyst for Dutch club AZ Alkmaar, where Beane has a 20 percent stake. “It’s how a club uses the information that makes the difference,” Gerrard added.
“The smarter clubs will interpret the data themselves to find out how a potential signing might go for them. Until recently, data-driven recruiting was an approach used by forward-thinking clubs to gain an edge over their rivals.
Now , due to the coronavirus pandemic and with revenues plummeting even at the wealthiest clubs, it is quickly becoming a necessity to find the right player at the lowest price. reports from last October, even Manchester United are now looking for a data scientist.
There are only so many Billy Beanes and Ian Grahams around – but data is available, lots of it. Cameras tracking players during live matches have been featured on every Premier League site since 2013, operated first by ChryonHego and since 2019-20 by Second Spectrum.
These cameras capture data at 25 frames per second and there are similar cameras in other European competitions. But the collected information is only available for clubs in the same league. Clubs should look elsewhere for data on players in foreign leagues.
Liverpool is collecting additional data from Skill Corner, a French analytics company that collects data from HD video feeds of every match in 21 competitions.
Data is collected by optical tracking algorithms, the kind used in rocket technology, that locate and record the position of each player and the ball every tenth of a second.
The system also calculates the movements of individual players and uses machine learning to train the algorithms to recognize players by their hair color, height and gait. Clubs get a ton of positional coordinates about each player at any point during a match, from which they can gain insights.
“A club might have six players they want to watch and ask us for data,” said Hugo Bordigoni, co-founder of Skill Corner. “They may want to be the fastest player in the Dutch league.
Or they could just access our road tracking data, which shows the distance players have traveled, how long they move at high intensity, the number of sprints made and peak speeds reached.
are other analytics firms that are working with an increasing number of football clubs to recruit players, which Gerrard says are gathering information or providing analytical insights, or both.
” Tim Mitchell, director of football analytics at DecTech, where Graham worked before joining Liverpool , explains that clubs use data to objectively assess how good a player is. “When a scout looks at a player, the image is subjective,” says Mitchell.
“People have limited memory, perceptions and cognition, we can’t compete. look and form a well-balanced objective assessment of how good a player is.”
To avoid costly mistakes, those responsible for transfers at football clubs need a deeper understanding of the potential of each potential signing.
“Data reconstructs the story of the match,” said Patrick Lucey, chief scientist at StatsPerform, a sports data and analytics company. “The more detailed the data, the better the story and the better predictions can be made.
” To establish an overall context, analysts look at the preferred style of play in the player’s current team, the opponents and generally in the league.
Is a physical approach common or do teams play a more agile game? Do teams defend deeply, put pressure on their opponents, prefer possession tactics or a direct approach? Does the potential new player come from a dominant or weaker team? Gerrard says, “The volume of work [a player does in a bad defensive team] doesn’t necessarily translate into quality or what the player can do for the new team, in a different system, where the player isn’t substituted always on as a defender.
” To understand what a player can actually do for his new team, analysts also need specific details about the player’s individual actions during matches and, most importantly, what happens around that player as they perform each action.
allows the analyst to extract data on a player that shows how they perform in the kinds of situations they might encounter at their new club.
It was this kind of analysis that enabled Liverpool analysts to see that Andrew Robertson had the potential to create a become a world-class left-back, even though he was part of a Hull City defense that had conceded 80 goals on their way to relegation last season.
Lucey explains that it is also possible for analysts to measure a player’s potential quality for a new team by simulating how the player would perform if he played in the new team’s system.
“We can see how the game would evolve around a decision, for example if we moved the back four forward (to defend further from goal, like many top teams do),” he says.
Mitchell adds, “To be useful, data needs to associate a value with each action and relate it to a team’s chance of scoring and conceding — a positive or negative value.
” All of this is a long way from the days when track-fit scouts stood in the rain with clipboards and a keen eye, making assessments of players who would inform, if not decide, a club’s transfer activities.
Wise old owls like Piet de Visser, now 83, who explored Neymar, Ruud van Nistelrooy, Kevin de Bruyne and Ronaldo (the Brazilian) before one of them was famous.
Or Geoff Twentyman, Liverpool’s chief scout during their period of dominance in the 1970s and 1980s, who helped bring in a troupe of unknown lower league players who would become stars. Keegan, Clemence, Rush, Hansen and many more.
The most famous of all old-school talent spotters died 30 years ago. Peter Taylor was Brian Clough’s assistant manager at Derby County and Nottingham Forest.
And it was his eye for a player, as well as Clough’s motivational skills, that helped two provincial clubs win national championships and, in Forest’s case, double European champions.
It was Taylor who scouted the apparently injury-prone and over-the-hill Dave Mackay as the man to get Derby into the First Division, found out future England defender Roy McFarland was playing in the Third Division, and helped overweight midfielder John Robertson turn into the best winger in the league.
There are many other similar stories and Gerrard thinks modern clubs, despite their increasing reliance on data, still need their Peter Taylors.
“A coach or scout with an in-depth understanding of the game will automatically contextualize what they see,” says Gerrard. “They see the whole picture and process information both analytically and instinctively.
Artificial intelligence relies solely on its programming and can only process the data.” A good scout can analyze things that data cannot quantify. A player’s ability to read the game, that talent that only a few have, to be in the right place at the right time to make a significant contribution.
The personality and attitude of a potential transfer target is something else that cannot be deduced from the data.
According to the football legend, Taylor once followed Birmingham City’s Kenny Burns to the dog track to see if Burns’ drinking and gambling was as bad as the rumours.
It wasn’t. Nottingham Forest signed him, Taylor and Clough turned the striker into a centre-back and in their first season together, Forest won the league and Burns was named Football Writers’ Player of the Year.
Talent spotters don’t always get it right, however. A certain Manchester United scout once claimed that Man United’s new Brazilian signing Anderson was a better player than Wayne Rooney.
Anderson scored a disappointing five goals in 105 games before being released, before falling into obscurity. The scout’s name? Martin Ferguson, Sir Alex’s brother. Gerrard proposes to combine data analysis and expert perspective as part of an evidence-based approach to player recruitment.
“Liverpool has scouts looking at players,” he says. “Even Billy Beane would look at potential concept choices. He wasn’t just relying on data.”
If another Premier League season kicks off, who will prove to make the best transfer decisions, and will they be based on the data or will they be scouted based on careful observation?
At the time of writing this article, the biggest transfer news was Manchester United’s proposed signing of Borussia Dortmund’s Jadon Sancho for a reported £73 million fee [which has now been completed – editor]; a big investment for a player of only 21, but he has already proven his abilities in the German Bundesliga and has huge promise.
The trick for United’s competitors is to use the data to find equal talent at a fraction of the cost.