The Impact of Algorithms in Cricket - Greenfield IT Recruitment

 

Cricket has moved with the times. Gone are the days where fans recorded game and player stats on a scorecard template. They now turn to their trusty smartphones to access endless data about the game in detail.

This sport is adored by millions of people from different cultures around the world. Even some of the most die-hard fans don’t fully understand all of the rules. For example, what happens when a match is interrupted by rain? (as it often does it in the UK).

We can all easily see what happens on the field as the covers are pulled out to keep it dry. The players make their way inside for refreshments to see the rain out. This eats into the allocated playing time for the game. Which is an issue for matches with limited-overs that have to be completed in one day. 

 

The System

This is where technology comes into play. As the playing time has to be reduced, the teams’ scores are also modified to adjust for the new allocated time. The system used to do this is called the DLS (Duckworth Lewis Stern) system. 

The DLS converts the number of overs remaining and the number of wickets lost into a resources remaining figure. As overs are completed or wickets fall, the remaining resources fall. The DLS uses this to calculate par score, from which teams’ actual scores are revised and matches decided.

“DLS tries to model various aspects of a game using equations and from this determine which team is in the ascendency at the time of the interruption.” Jehangir Amjad, a cricket-mad lecturer in machine learning at Massachusetts Institute of Technology.

However, Amjad found that DLS had a statistically significant bias in favour of the chasing team post-rain interruption. Because of this, Amjad created his own system which predicts the final score and which team is in the ascendancy. It also predicted what was most likely to happen for the rest of the game had the match continued without interruption. 

This technique, also known as robust synthetic control, goes beyond just a game of cricket. It is mostly used in economics, health policy and political science to evaluate the effects of an intervention. Amjad claims that the benefit of examining a problem this way means that limited or missing data is not an insurmountable obstacle.

 

Factoring In Luck

The DLS system is an accurate modifier based on the data it has received. However, so often is the case that luck has a major impact on the momentum of the game and swing the overall result into an unforeseen outcome. 

Researchers from Indian Institute of Technology Madras Gyan Data Pvt. Ltd, a local IT start-up, has been working with cricket website ESPN Cricinfo to find a way of quantifying the effect of luck on cricket matches.

They outlined two major luck events for a batter, a dropped catch and an edge for four. A third generic luck event that covers any other fortunate occurrence was also included. This could be a bowler beating the bat often without getting a wicket. A wicket taken from an unpredictable bounce or an umpiring error.

In order to factor luck on a game, the algorithm considers what has previously happened in past matches and plays out different scenarios. It evaluates what the impact of luck events would be. For example the runs a batter scores after a dropped catch count as lucky runs.

 

The Need For More Data

The investment made in cricket over recent decades is driving companies to look for new ways of maximising their returns. The ability to extract and utilise data can be seen in all areas of the game. A few examples are included below:

  • Microsoft – Currently producing a smart bat that will transfer data about the batter’s shots to fan’s mobile phones. 
  • India World Cup Team – GPS trackers to measure their player’s fitness
  • CricViz – A cricket intelligence app aimed at fans that uses Hawkeye data modelling to provide real-time data about player performance during games.

 

Is Technology Harming The Game?

Critics will say that cricket is becoming too predictable with all the technology and analytics surrounding the modern game. 

This isn’t the case according to Liam Sanders, a former England and Wales Cricket Board Member. He adds that providing real-time data helps the sport engage with younger fans. “People’s attention spans tend to be shorter these days,” he says. “Do things in the same old way and people will just switch off.” 

Ultimately, it seems as though the level of complexity in a game of cricket lends itself quite nicely to the benefits that technology has to offer. As a result of this, and the numerous factors that impact on the outcome of any event during a single game. Fans want finer details on their players and the potential outcome. Given the sheer amount of money being pumped into the modern game, it looks likely that these changes will go on to have a bigger role in the future of cricket. 

Greenfield IT has a team dedicated to recruiting tech and digital skills for the sports industry. We support a number of major UK sports clubs and governing bodies. But we also work with a number of sports tech firms whose products and services are focused on the sector.

Follow us for selected sports industry tech insights and career opportunities in this space. To find out more about how we can help your career in sports tech, or should you require support building your team. Contact Eleanor Carter.