How England’s cricket coaches are using AI to help pick their teams, with off-spinner Charlie Dean proving a huge success against Australia

When England women’s head coach Jon Lewis recently revealed that team analysts had used artificial intelligence to inform the squad for last summer’s Ashes, it sounded like another nail in the coffin for the traditional talent scout armed with binoculars, notepad and instinct.

But the use of software from London company PSi to simulate 250,000 match-game permutations is just part of an ongoing revolution in the way cricket coaches and selectors make their decisions.

Lewis, who concluded that off-spinner Charlie Dean should be in the T20 squad – a move that played a role in England’s thrilling comeback against Australia – was happy to let the technicians do their work.

Artificial intelligence (AI) has of course become an abused term, not least because of a now well-known doomsday scenario: one day it will make us all unemployed. Paul Hawkins, founder of Hawk-Eye ball-tracking technology, defines AI as “making computers do things that humans consider intelligent.” He adds, “Washing machines were once considered AI.”

And without massive amounts of data for computers to process, the concept would be obsolete. Yet Hawkins has played a part in the next big wave of data collection in the English game, thanks to his iHawk GoPro camera, which has been attached to the jackets of referees in county matches since the start of last season, allowing close-ups assessment of each ball: how much it swings, seams or turns, how fast it moves and where it passes the bat and stumps.

Charlie Dean proved an AI success story after sparking England’s comeback against Australia

For Stafford Murray, a former junior squash champion who now leads the ECB’s England men’s data analytics team, the technology has been groundbreaking.

“We can now start to give this in-depth, contextualized information to the selectors,” he says. “We can tell them, ‘You know what, if we put these players in certain international conditions, there’s a good chance they’ll be more successful than if we just look at averages and traditional statistics.'”

Data from iHawk has already made its presence felt. Last summer it confirmed that the fastest bowler in the county championship was Josh Tongue of Worcestershire, who made a five-out Test debut against Ireland and then removed David Warner and Steve Smith twice each in the Lord’s Ashes Test.

Hampshire’s unheralded John Turner was also catapulted into the international battle for the white ball due to iHawk’s readings of his pace.

And while Brendon McCullum and Ben Stokes are less keen on number-crunching than their white-ball counterparts, Matthew Mott and Jos Buttler, the decision to take Lancashire’s uncapped spinner Tom Hartley on England’s Test tour of India was backed by iHawk data showing it turned out his release point was similar to that of the home side’s slow left-armer Axar Patel, who had tormented England on their previous visit.

For Mott and Buttler, the use of data to inform ‘match-ups’ – the prospect of one player’s success against another – is deeply ingrained, to the extent that Freddie Wilde, the highly regarded white-ball teams analyst, got involved is at selection meetings. His examination of what England can expect, in terms of opponents and conditions, next month when they defend their T20 world title in the Caribbean, will be crucial.

Still, Murray emphasizes, “It’s not about making a decision for the domain experts, the coach and the captain. It ensures that the conversation is informed by data. We are not data-driven or data-led: we are data-informed.’

Central to the approach is the idea that batting and bowling averages only tell part of the story. “The data I love is finding out someone’s true impact and quality,” says Rob Key, ECB director of men’s cricket.

Brendon McCullum and Ben Stokes are less focused on numbers among the men

“Find out who that bowler is who may not be getting wickets on a given day, but is actually applying more pressure than anyone else, and because of them, bowlers at the other end are getting wickets.

‘Or the batsman who has endured the most brutal of spells without perhaps the return of a hundred on the day, but without that ball the side would have capitulated. It’s about finding the players in domestic cricket who have the qualities needed for international cricket, and this kind of data is useful.”

Two years ago at Old Trafford, Zak Crawley hit 38 grounders in 36 overs against a top-flight South African attack, helping England – one down in the series – from 43 for three. The praise he received from teammates felt at the time like an attempt to boost a struggling player’s confidence. Yet his innings, which laid the foundation for hundreds from Stokes and Ben Foakes, ticked the ‘impact’ box that is now a buzzword for Murray and Key.

For example, if the data generated by iHawk shows that a seam is adept at breaking through with the old ball on a flat pitch, then their impact in a test in Australia is likely to be greater than that of a seam that only thrives when the ball is fresh and pitch green.

Murray explains how the concept of impact can help drive selection. ‘Firstly, our philosophy is to help substantiate decisions in a predictive manner, where necessary, so that they are future-oriented. We look at what will happen after we have learned from what happened. ‘Secondly, the data is often post-match, and this data is essential for debriefing and reflection, but where possible we want to inform decisions and conversations in the moment, to have real-time impact during matches.’

“Finally, it’s about using these techniques to ensure we’re collecting data across the entire player journey, so the best talent gets to the top. And that’s where measuring quality and impact is really big for us. It is a gigantic data science project.”

He adds: “When we say impact, it comes down to: what did that spell, or a player’s particular action, have on the odds of winning? How did it change the odds of success over that period? There’s a lot of math behind that, but that’s basically what we do.’

Murray laughs when the analogy is presented to him, but he admits that this approach broadly mirrors the expected goals calculation in football.

AI is less new than many realize. In 2010, then English analyst Nathan Leamon, a Cambridge mathematics graduate, devised a system called Monte Carlo, which used existing data to simulate the outcome of matches. WinViz, the earnings forecaster created by Leamon’s company CricViz, does something similar.

And Leamon caused a stir during a T20 series in South Africa in late 2020 when he placed numbered cards on the dressing room balcony to aid Eoin Morgan’s on-field decision-making. However, the English position on data is the same as it was then: it is there to help, not to dictate.

The decision to take Tom Hartley on England’s Test tour of India was backed by iHawk data

“Predictive analytics will be a big challenge to monitor over the next six to 12 months as it really comes into play as AI methodologies and technologies evolve,” Murray says.

“I’m not Bill Gates, but the way I see AI having the most impact for us is that we have more real-time information, which allows us to better predict and measure the trajectory in a more sensitive or in-depth way, to better to inform selection.”

‘But you can’t replicate what the skipper can see, feel, smell and taste on the pitch. There are always contextual things going on that the numbers can’t measure. And that’s why it will never replace those people’s decisions. And that’s the fun part. If you could measure everything, it would be a bit boring.’

The analysts are not without work. Yet.