Use of Artificial Intelligence (AI) in football – nation.lk – The Nation Newspaper

Former Premier League midfielder Matt Oakley, seen here in action for Southampton in 1999, is a key backer of the AI tool

This does not mean that the human touch and experience needed to make these decisions are totally redundant

Artificial Intelligence, also known as AI, is a subject that has been spoken about in the world a lot, these days. There have been quite a few doomsday predictions where it has been projected that the machines will totally take over the functions of human beings as well.

Be that as it may, AI is defined as the simulation of human intelligence in machines that are programmed to think like humans and mimic their actions.

The term AI may also be applied to any machine that exhibits traits associated with a human mind such as learning and problem-solving.

Uses of AI

There are four types of Artificial Intelligence. They are (i) Reactive machines, (ii) Limited memory, (iii) Theory of mind, and (iv) Self-awareness.

AI enhances the speed, precision, and effectiveness of human efforts. In financial institutions, AI techniques can be used to identify which transactions are likely to be fraudulent, adopt fast, and accurate credit scoring, as well as automate manually intense data management tasks.

There has been wide speculation as to how this can be used in sports.

Take smarter decisions?

In an earlier column, this writer presented an article regarding the use of a vest for data collection of athletes.

And, if the data collected during these matches, can they be used to feed the machines. Then could AI be used to make smarter decisions regarding players, by the coaches, clubs, and national sports bodies.

This has been the question that has been discussed and is being discussed at all levels of sports in the more advanced countries.

The answer to that question seems to be yes, judging from the results of the use of AI in the England Premier League football during last season. But one successful prediction is not conclusive evidence in any circumstance. And the accuracy of its predictions still makes reads rather scary reading.

Real Analytics

Former Southampton midfielder Matt Oakley and Professor Ian McHale of the University of Liverpool are behind the recruitment tool, Real Analytics, that they believe will revolutionise the way in which clubs obtain and retain players. Oakley has a very impressive background in football after having played for a number of Premier League clubs in his playing days.

Oakley, who made nearly 700 senior appearances for the likes of Southampton and Leicester, says: From my perspective as a former player, seeing what Ian can do is so exciting. This is completely different, that ability to predict the impact of results on a specific team. But it also helps in knowing when to sell a player. The analysis gives an unbiased view, all based on what a player does on the pitch.

Scouts should use data and vice versa

But as Oakley says: There is a definite resistance from some Managers towards data. I have seen it, but we are striving to bridge the gap between data and football. We have data on 150 leagues and 40,000 players. It is about turning that into useful information. At the moment, we believe people arent using it to its full advantage. That is not to say the traditional scout should be made redundant. Scouts should use data and data should use scouts. For example, a man in the stand can tell you more about body language and when a players head drops. We know there is more to it than numbers.

Scarily correct predictions

Professor Ian McHale of the University of Liverpool who created the technology that tells you what will happen, not what has happened

They spoke then of how, last summer, they were asked to run a player impact report on Pierre Emerick Aubameyang, prior to Arsenal football clubs decision to award him a lucrative new contract, worth 55 million (Rs. 15 b) over three years.

After all, Aubameyang had been their leading scorer and talisman at the club. Oakley and Prof. McHale however warned how keeping the striker at the club was perhaps not a prudent move.

Their system, Real Analytics, predicted that Arsenal would finish in an average of eighth position in the Premier League with Aubameyang in the squad, and ninth without him. It also projected that they would score 55 goals with, and 50 without. Arsenal finished eighth, with a goals tally of 55.

How does it work?

So how does this work? As McHale explains, all the readings are in the data itself.

The numbers that go into it are called event data. Every match has around 2,000 events. A pass is not just recorded as a pass. We have the x-y co-ordinates of where the pass came from and where it went and who it went to.

Our AI engine learns the value of every action in terms of what it contributes to the likelihood of that possession ending in a goal. Every pass, every tackle, every interception, everything is given a positive or negative score.

Originally from gambling industry

Real Analytics claims to be the future of decision making in football

He further went onto say, It can be used for coaching to look at the moments where you have added value, or it can deem that you have taken value away. You can see how some players, who might be completing lots of passes, actually impact negatively on the team.

But when it comes to recruitment, it is no use knowing how good a player was last week. We need our tools to be predictive. We want to know how good he will be next year, or in five years time. It turns out things like pass completion percentage reveal little about a players future performances.

We have been working on these types of models for 20 years. They were originally built for the gambling industry and designed for forecasting the outcome of matches. We realised that all the tools we were building, we could use them for the football industry, with a few tweaks.

Conclusion

This is only one of the predictions of a number of others that came in correctly as predicted by Real Analytics. This does not mean that the human touch and experience needed to make these decisions are totally redundant.

But what it does mean is that Artificial Intelligence or AI can be made use of by the humans to make better-informed decisions.

Continued here:

Use of Artificial Intelligence (AI) in football - nation.lk - The Nation Newspaper