Researchers at the Indian Institute of Technology Madras (IIT-M), along with colleagues at sports news site ESPNcricinfo, have developed Superstats, a combination of statistical metrics that use data science to give a context to every event in a cricket match.
The machine learning algorithms use forecasting methods that are trained on past data to reveal trends and patterns during different periods of play and adapt based on actual match data to create predictive models.
The tool was designed using ESPNcricinfo's ball-by-ball database containing over 10 years of data.
The algorithms process this data and analyze the real value of a player's performance in real time.
Said IIT-M researcher Raghunathan Rengaswamy, "These algorithms rationalize and consistently quantify luck events so that a whole tournament with matches that occurred in disparate circumstances could be compared in an 'apples-to-apples' fashion."
From The Economic Times
View Full Article
Abstracts Copyright © 2019 SmithBucklin, Washington, DC, USA