Scouting’s Civil War: Will Data or Human Instinct Find Football’s Next Superstar?

In any industry, people who disparage technology’s worth are labelled Luddites and told to accept their new place in the world, but should we consign the people who are tasked with finding the football stars of the future to this same fate? We consider whether data or human instinct will lead us to the next star of the beautiful game

Every professional football club is looking to find the next Cristiano Ronaldo or Lionel Messi; players who make the beautiful game look stupidly simple and bewilderingly complex at the same time.  Where clubs differ, though, is in the methods they use in their search for the sport’s next megastar. Some clubs rely on a data heavy approach – seemingly inspired by Michael Lewis’s book Moneyball: The Art of Winning an Unfair Game, which described how, by meticulously choosing stats the baseball establishment had previously ignored, the Oakland Athletics baseball team were able to compete with wealthier teams. Other clubs, however, prefer the old-school approach of sending a flat-cap sporting scout to watch new recruits kicking a ball around so they can judge them with their own two eyes.

Neither method is beyond reproach, but does one have a distinct advantage over the other? Critics of Moneyball – or what generally passes for Moneyball in football – would cite the case of Aston Villa, who former manager Ron Atkinson described as: “The club that has suffered more in the pursuit of Moneyball than any other in recent times.”

Villa relied heavily on statistical analysis to scout players and seemingly didn’t place much value in having people on the ground looking at players. To give you some idea of how Aston Villa’s scouting department worked, the club’s head European scout, whose main focus was players in the German Bundesliga, allegedly emigrated to Australia and continued to do his job. This approach to identifying player talent didn’t work for Villa (who would’ve guessed) and the club was relegated from the Premier League with the third worst points tally in the competition’s history.

On the other hand, the more traditional way of scouting players also has a number of criticisms levelled against it, many of which essentially come back to the same point: how reliable are a scout’s own subjective, open-to-interpretation conclusions if they aren’t supported by data?

Speaking at the Wearable Technology Show 2017, Peter Tierney, sports scientist and former scout who now works as head of operations for Axsys Performance, described how the coach’s eye led to the existence of a kind of size bias in children’s football. “One of the key tools that has been used over the years is the coach’s eye. It’s good, but it also can also be bad because if in doubt what we ended up doing was going with the biggest all the time,” said Tierney.

Can you spot intelligence?

The accusation that scouts favour physical attributes over characteristics like intelligence, creativity and drive – difficult things to spot during a Saturday morning match – has plagued scouts for years, and has led some to call for young footballers to be organised according to their physical maturity rather than their age, in a technique called ‘bio-banding’.

Previously, Tierney was involved in a talent acquisition for rugby rather than a football and found that, for obvious reasons, rugby scouts are even more susceptible to size bias. In one programme he ran, 85.7% of the intake of future rugby players were born in the first half of the academic year. It’s understandable that scouts would be drawn towards children who already demonstrate skills which will be useful when they reach professional level, so older children, with their physical advantages, will be favoured over children born later in the year, who will always be playing catch up, unless techniques like bio-banding are adopted more widely.

Legendary footballer Andrés Iniesta playing for Spain against Chile. Image courtesy of Clément Bucco-Lechat

Having made the switch to football, Tierney points out that the same problems exist there too. “Children that were born in the first half of the year tended to be more successful in being identified than those born later in the year,” he said. “It depends where you are in the world because different parts of the world have different ways of grouping [children]. In the UK, for example, we group the children from September to August, and when they enter primary school they’re instantly put into those year groups.

“What we’ve found is that children who are born between September and December, they’re the ones that are predominantly playing football at a higher level than those that are born later in the year.”

One club that doesn’t appear to have scouts who pick players based on their physicality is also arguably the best side in world football: FC Barcelona. Raul Pelaez, head of sports technology at FC Barcelona, explains the criteria it uses to choose players by highlighting the example set by one of its most successful graduates from its famed La Masia academy, Andrés Iniesta.

“Iniesta is not endurance, he’s not a speeder, he doesn’t score goals. Iniesta only now hopes to play,” says Pelaez. “For us it’s not important if the player is thin, is fat, t’is speed and endurance. We need that he’s intelligent, and maybe the difference between FC Barcelona players and the rest is that he understands a little bit better the play, what happens in the play, what happens in the direction of the match.”

Increasing the talent pool

For a long time clubs like Aston Villa got scouting very wrong. Its aversion to sending scouts to do the hard yards and actually watch players, while marking them against a criteria which promotes intelligence and seeks to avoid physical bias, like FC Barcelona does, was clearly an incorrect approach. But there are examples of clubs who successfully use data and tech to identify some of the best players in the world.

It’s our core business to find the best players at an early stage

Like many modern elite football teams, Portugal’s SL Benfica analyses every aspect of its players’ lives, whether they’re working or at home relaxing. The club looks at its players’ eating and sleeping habits, how fast they run, tire and recover and their mental health. No stone is left unturned in the pursuit of making Benfica’s players better. All this data collecting has a point, though, because Benfica considers itself an elite club, but even finishing atop Portugal’s Primeira Liga doesn’t give you the resources needed to compete much wealthier football clubs like Manchester United or Real Madrid. So Benfica has taken its data-driven approach to talent acquisition and improvement and come up with a new revenue stream.

“It’s our core business to find the best players at an early stage,” Benfica chief executive Domingos Oliveira said in an interview with The National. “We try to anticipate the player’s future at the early stage of their development.

“We’ll not buy a player at 26 or 27, but 18 or 19,” adds Oliveira.

Benfica are by no means the only club using data to talent spot, but they are certainly one of the most successful. Already this summer Benfica have sold two players to the Premier League, for a combined total of almost £75m. Add that to previous year’s sales and Benfica have made well over £300m in the last seven years.

Tierney himself is a fan of using data as a method of increasing the size of the talent pool available to clubs. “The benefits of using all this technology now that’s readily available and using things such as your mobile devices is it will increase the size of the talent pool, which has been ever decreasing,” said Tierney. “It allows for earlier identification of potential talent, will help with a more qualitative analysis and it will give clarity because there is not so much scout reliance.

The people who matter

If being relegated as one of the worst teams ever to compete in a competition doesn’t alert you to the fact that something is drastically wrong in your organisation then nothing will, so because of its disastrous season Aston Villa has been forced to take drastic steps to improve the way it identifies talent. Sensibly, the club has gone back to sending scouts out to watch football games and allowing them to spot football’s next superstar. Rather than relying on data and statistics, or results thrown up by using the Moneyball method, these things are now used to back up the opinion of scouts rather than supplanting them.

“We’ve brought in real football people and we’ll mix that with one or two of the guys that have the analytical, Moneyball data that you hear about,” said Steve Round, Aston Villa’s new director of football in an interview with Aston Villa’s supporters club.

“The Moneyball thing came about because of baseball and that’s very statistically developed – like cricket. But football is always in a state of chaos. On any given day, football is a random, human, fluid game, so data and analytics only back up the instinct of the people looking for the talent,” said Round.

“I think football has gone away from that. They’ve gone too analytical and too data-minded, and a lot of people are paying the price for it. You’ve got to get back to the real people who matter. Scouts identify the talent and data backs that up. Villa is a massive club with high expectations, our scouts with a massive knowledge on football need to know that a particular player is capable of thriving at our club.”

In truth, the idea that there was ever another way to identify talented players was a bit of a fallacy. That’s not to discredit data analysis: as US soccer’s high performance director, James Bunce, points out, a player taken on by an academy at eight-years old has a 200-to-1 chance of making the first team, so it’s right that he best clubs collect as much data as possible so that they can make informed choices about which players will be able to survive as professional footballers. That being said, it’s also important we don’t forget the flat-cap sporting scout who has been to watch a million children, playing in hundreds of parks, on a thousand cold Saturday mornings. They have a wealth of knowledge, and football clubs would be foolish to ignore it.

Scientists, software developers and artists have begun using VR to visualise genes and predict disease

A group of scientists, software developers and artists have taken to using virtual reality (VR) technology to visualise complex interactions between genes and their regulatory elements.

The team, which comprises of members from Oxford University, Universita’ di Napoli and Goldsmiths, University of London, have been using VR to visualise simulations of a composite of data from genome sequencing, data on the interactions of DNA and microscopy data.

When all this data is combined the team are provided with an interactive, 3D image that shows where different regions of the genome sit relative to others, and how they interact with each other.

“Being able to visualise such data is important because the human brain is very good at pattern recognition – we tend to think visually,” said Stephen Taylor, head of the Computational Biology Research Group at Oxford’s MRC Weatherall Institute of Molecular Medicine (WIMM).

“It began at a conference back in 2014 when we saw a demonstration by researchers from Goldsmiths who had used software called CSynth to model proteins in three dimensions. We began working with them, feeding in seemingly incomprehensible information derived from our studies of the human alpha globin gene cluster and we were amazed that what we saw on the screen was an instantly recognisable model.”

The team believe that being able to visualise the interactions between genes and their regulatory elements will allow them to understand the basis of human genetic diseases, and are currently applying their techniques to study genetic diseases such as diabetes, cancer and multiple sclerosis.

“Our ultimate aim in this area is to correct the faulty gene or its regulatory elements and be able to re-introduce the corrected cells into a patient’s bone marrow: to perfect this we have to fully understand how genes and their regulatory elements interact with one another” said Professor Doug Higgs, a principal researcher at the WIMM.

“Having virtual reality tools like this will enable researchers to efficiently combine their data to gain a much broader understanding of how the organisation of the genome affects gene expression, and how mutations and variants affect such interactions.”

There are around 37 trillion cells in the average adult human body, and each cell contains two meters of DNA tightly packed into its nucleus.

While the technology to sequence genomes is well established, it has been shown that the manner in which DNA is folded within each cell affects how genes are expressed.

“There are more than three billion base pairs in the human genome, and a change in just one of these can cause a problem. As a model we’ve been looking at the human alpha globin gene cluster to understand how variants in genes and their regulatory elements may cause human genetic disease,” said Prof Jim Hughes, associate professor of Genome Biology at Oxford University.

Using CRISPR, UK scientists edit DNA of human embryos

For the first time in the UK, scientists have altered human embryos. Using the gene-editing tool CRISPR, the scientists turned off the protein OCT4, which is thought to be important in early embryo development. In doing so, cells that normally go on to form the placenta, yolk sac and foetus failed to develop.

Source: BBC

Tesla and AMD developing AI chip for self-driving cars

Tesla has partnered with AMD to develop a dedicated chip that will handle autonomous driving tasks in its cars. Tesla's Autopilot programme is currently headed by former AMD chip architect Jim Keller, and it is said that more than 50 people are working on the initiative under his leadership.

Source: CNBC

Synthetic muscle developed that can lift 1,000 times its own weight

Scientists have used a 3D printing technique to create an artificial muscle that can lift 1,000 times its own weight. "It can push, pull, bend, twist, and lift weight. It's the closest artificial material equivalent we have to a natural muscle," said Dr Aslan Miriyev, from the Creative Machines lab.

Source: Telegraph

Head of AI at Google criticises "AI apocalypse" scaremongering

John Giannandrea, the senior vice president of engineering at Google, has condemned AI scaremongering, promoted by people like Elon Musk ."I just object to the hype and the sort of sound bites that some people have been making," said Giannandrea."I am definitely not worried about the AI apocalypse."

Source: CNBC

Scientists engineer antibody that attacks 99% of HIV strains

Scientists have engineered an antibody that attacks 99% of HIV strains and is built to attack three critical parts of the virus, which makes it harder for the HIV virus to resist its effects. The International Aids Society said it was an "exciting breakthrough". Human trials will begin in 2018.

Source: BBC

Facebook has a plan to stop fake news from influencing elections

Mark Zuckerberg has outlined nine steps that Facebook will take to "protect election integrity". “I care deeply about the democratic process and protecting its integrity," he said during a live broadcast on his Facebook page. "I don’t want anyone to use our tools to undermine our democracy.”