PandaScore drops PandaSkill for League of Legends

PandaScore, the award-winning provider of esports data, odds and betting products, has rolled out an exciting player performance and skill rating system for League of Legends.

PandaSkill has been developed by PandaScore’s data science team and aims to uplift performance analysis and product performance.

It is a machine learning model that measures individual player skill in a way that more accurately compares every player, accounting for their respective roles and, crucially, measures the skill of players relative to the strength of every player across the world.

Each in-game role is modelled independently, ensuring a fair comparison between them. Then, using these performance scores, PandaSkill updates the player skill ratings using the Bayesian framework OpenSkill in a free-for-all setting

In this setting, skill ratings are updated solely based on performance scores rather than game outcomes, highlighting individual contributions.

PandaSkill has been developed as an open-source resource that can be used for the betterment of the wider industry.

It can be deployed across websites, apps or within the context of an esports publication and can be used by fans and bettors to compare players, teams and performances over time to guide their wagers, adding more interest and value to the community.

As well as adding value to PandaScore’s operators and their players, the provider is also using it to improve its offering.

PandaSkill is supporting the provider’s core esports betting services, especially its popular Player Props and BetBuilder as it helps to increase the accuracy of its odds by bringing them closer to true probability, as well as informing its traders as to how the probabilities are being created.

Oliver Niner, Head of B2B at PandaScore, said: “The idea for PandaSkill was borne out of a culture of understanding games at an intrinsic, data-driven level, what drives wins and what constitutes good or bad performance. 

“Esports fans a bettors share a similar interest in data-driven performance, whether that be their personal ratings and rankings in the games they play or the latest stats for the best pro players in the world. 

“PandaSkill takes this to the next level, helping inform public discussion, culture building and broadcast commentary, as well as helping players make smarter bets while also allowing us to improve the products and services we offer to operators. 

“This makes PandaSkill an important product in our suite. It also stands as a testament to our commitment to be at the cutting edge of esports and esports betting.”