Machine Learning (ML) based Advanced Kabaddi Metrics for PKL – Part 2

Machine Learning (ML) based Advanced Kabaddi Metrics for PKL – Part 2

Kabaddi needs a more evolved and a more nuanced system which adds more meaning to the numbers by measuring the net impact they have on the game.

Advanced Kabaddi Metrics-Part 1 featured the introduction of the True Raider Impact (TRI) metric which helped to better evaluate the performance of raiders.

Here in Part-2, we introduce two new ML based metrics – In Game -Win Probability and xRaids

In Game – Win Probability

A win probability is a likelihood that, given any time-state in the game, a certain team will win the game. While it’s not a case of saying this is definitely going to happen, it’s providing an insight into what is likely to happen given the various in-game situations the teams are under.

We have built an in-game win probability model for the raiding (attacking) team during a Kabaddi game. In-game win probability in Kabaddi is a statistical metric that provides a team’s likelihood of winning before any given raid. The model can serve as a tool in making in-game decisions by evaluating the team’s performance in crucial game situations while also assisting in crafting strategies, and also in fan engagement for broadcasters.

To make this prediction, we train our model using event data from the last three seasons of the Pro Kabaddi League comprising 413 matches and 35356 events(raids). It takes into account various factors such as

  • Score difference,

  • Time remaining,

  • Number of raiding team players on the mat at any given raid

  • Number of defending team players on the mat at any given raid

  • How long each team has been rested before the game

  • The playing venue.

xRaids

Lastly, we come to a metric that is still in the works in xRaids.

xRaids attempts to predict the number of raids a player is likely to attempt in the upcoming season. Since WPM (Win Probablity Model) and TRI (True Raider Impact)  are raid-level projects, we wanted to extrapolate it to the season level, for which we will need a measure of the volume of raids.

It also helps to project the performance of raiders based on the number of raids they are likely going to attempt in the upcoming season and identify the players who are less likely to get out, to make better team selections.

Stay tuned for updates on xRaids on our social media platforms!

With Season 8 of the Pro Kabaddi League on the horizon, be on the lookout for more insights and analysis from our team.

Pic Credit : Prokabaddi.com