Researchers at the Indian Institute of Technology-Madras (IIT-M) have found a way for fans to analyse limited-overs cricket matches, like experts.

The researchers have used ESPNcricinfo’s ball-by-ball data to develop a method for fans to analyse the ongoing Indian Premier League (IPL) matches.

The AI tool was developed in 2019 through a collaboration between IIT-Madras, ESPNcricinfo and Gyan Data, a company incubated at the institute.

The collaboration led to the development of a tool that uses a set of metrics to assess performances of teams in limited-overs T20 and ODI matches.

Statistical and machine-learning models are used to forecast the final score of an ongoing innings. Factors such as current run rate, number of overs, remaining wickets, and the quality and form of players are considered.

The analysts have included a “luck index” to quantify the impact of events, such as dropped catches and umpiring errors, on the final score and match result.

Three metrics — smart runs, smart wickets and impact score — that affect the players’ performance and the opposition’s batting quality and bowling performance have also been used for the analysis.

Superstats is a key ingredient of the 2020 plan, as it was in IPL 2019, according to S. Rajesh, stats editor at ESPNcricinfo.

“Since it is a bouquet of offerings, these stats metrics will enhance all aspects of coverage prior to, during and after the game,” Mr. Rajesh said.

Raghunathan Rengaswamy, dean of Global Engagement, who leads the team with Mahesh Panchagnula, dean, alumni and corporate relations, said: “These kinds of projects also reaffirm our faith in the universality of machine learning and data science techniques that we develop and its application potential in multiple fields.”

ESPN India and South Asia vice-president Ramesh Kumar said the use of data-driven tools in sports had given them an edge in presenting content, “bringing various nuances of the game in the right context and providing the complete picture to the users”.

Maheshwarran Karthikeyan, lead data scientist and a cricket enthusiast who worked on the 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 analyse a cricket match just like an expert.”