For the fourth time in five years, Stats Perform had a research paper, authored by the company’s AI team, shortlisted as a finalist in the research track at the 2020 MIT Sloan Sports Analytics Conference.
The paper, titled “You Cannot Do That Ben Stokes: Dynamically Predicting Shot Type in Cricket Using a Personalised Deep Neural Network”, introduces a new model for dynamically predicting a batsman’s shot type in One Day International cricket, using ball-by-ball Opta event data.
One of the authors of the paper, Dr. Will Gürpınar-Morgan, delivered a presentation at the event which focused on deliveries bowled by Trent Boult to Ben Stokes during the memorable final over of the 2019 Cricket World Cup Final.
Through applying the model, the presentation outlined the probabilities of shot type from each ball and their-end location, highlighting the most likely outcome. The model takes into account various factors, including the game state, the bowler’s delivery trajectory and various personalised metrics for the batsman.
The full presentation is available to watch below.
If you are interested in reading the full research paper, which was co-authored by Dr. Gürpınar-Morgan, Dr. Daniel Dinsdale, Dr. Joe Gallagher, Mr. Aditya Cherukumudi and Dr. Patrick Lucey, please click on the download link below.