AI-powered ‘Superstats’ enhancing the IPL Experience for Fans
Chennai: Indian Institute of Technology Madras and ESPNcricinfo’s Artificial Intelligence Tool ‘Superstats’ is once again enhancing the fans experience of Indian Premier League (IPL) matches. It uses data science to give a context to every event in a game and also provides insights into factors such as ‘luck.’
ESPNcricinfo had partnered with IIT Madras to co-develop an AI Engine that leverages the rich data collected from over a decade-old ESPNcricinfo’s ball-by-ball updates. Developed in 2019 through a collaboration between ESPNcricinfo, IIT Madras and Gyan Data Pvt. Ltd., an IIT Madras-incubated company, the tool is a suite of metrics that helps fans judge performances in limited-overs cricket – T20s and ODIs – in a far more nuanced manner than conventional metrics do.
The ‘Forecaster’ predicts the final score of an ongoing innings and the win probabilities of teams using statistical and machine learning models. The predictions take into account several factors including the current run rate, number of overs and wickets left, quality and form of the players. The ‘Luck Index’ is a first-of-its-kind concept in cricket analytics that quantifies the impact of lucky events (such as dropped catches and umpiring errors, among others) on the final score and match result. The ‘Smart Stats’ is a set of three novel metrics – Smart Runs, Smart Wickets, and Impact Score – that factor in the pressure on a player and opposition quality for evaluating batting and bowling performances.
Highlighting the role of this AI-driven tool, Mr. S. Rajesh, Stats Editor, ESPNcricinfo, said, “Superstats was a significant part of ESPNcricinfo’s stats coverage of IPL 2019 and will be a key ingredient of the 2020 plan as well. Since it is a bouquet of offerings, these stats metrics will enhance all aspects of coverage: pre-game, in-game and post-game.”
IIT Madras Researchers and Gyan Data working with cricket experts from ESPNcricinfo derived Superstats from ESPNcricinfo’s database and scientific methods, processes and complex algorithms based on machine learning. The algorithms process accurate, fast data, quantify the impact of luck and analyzes the real value of a player’s performance in the game of cricket in real-time. The work was led by Prof. Raghunathan Rengaswamy and Prof. Mahesh Panchagnula of IIT Madras along with the ESPNcricinfo team.
Speaking about the contribution of IIT Madras in developing this AI Engine, Prof. Raghunathan Rengaswamy, Dean (Global Engagement), IIT Madras, said, “It has been a wonderful experience to be a part of this effort from IIT Madras. These kinds of projects also reaffirm our faith in the universality of the machine learning and data science techniques that we develop and its application potential in multiple fields.”
Further, Prof. Mahesh Panchagnula, Dean (Alumni and Corporate Relations), IIT Madras, said, “Our relationship with ESPN is strong and still growing from strength to strength. I expect more in the future out of this relationship.”
Superstats takes into account the context of every performance, batting and bowling. Context includes pitch conditions, quality of opposition, and match situation – in terms of the pressure on the player.
Speaking about this collaboration, Mr. Ramesh Kumar, Vice President and Head, ESPN (India and South Asia), said, “The use of data science driven tools in sports have helped us to offer a much more enriching content experience to our discerning fans and cricket enthusiasts. It has given us a distinct edge in the way we present the many layers of content, bringing the various nuances of the game in the right context, and providing the complete picture to our users. It also helps us to further establish our unique brand proposition of being a much more astute cricket platform going beyond just the scores”
These data science algorithms use forecasting methods that train on past data to uncover trends and patterns during different periods of play and adapt based on actual match data resulting in highly accurate predictive models.
Mr. Maheshwarran Karthikeyan, Lead Data Scientist and a die-hard cricket enthusiast who worked on this project said, “Thanks to the increasingly popular field of data science and ESPNcricinfo’s rich ball-by-ball data, it has been possible to develop complex data-driven algorithms that analyze a cricket match just like an expert.”