Abstract
AbstractVast data on eSports should be easily accessible but often is not. League of Legends (LoL) only has rudimentary statistics such as levels, items, gold, and deaths. We present a new way to capture more useful data. We track every champion’s location multiple times every second. We track every ability cast and attack made, all damages caused and avoided, vision, health, mana, and cooldowns. We track continuously, invisibly, remotely, and live. Using a combination of computer vision, dynamic client hooks, machine learning, visualization, logistic regression, large-scale cloud computing, and fast and frugal trees, we generate this new high-frequency data on millions of ranked LoL games, calibrate an in-game win probability model, develop enhanced definitions for standard metrics, introduce dozens more advanced metrics, automate player improvement analysis, and apply a new player-evaluation framework on the basic and advanced stats. How much does an individual contribute to a team’s performance? We find that individual actions conditioned on changes to estimated win probability correlate almost perfectly to team performance: regular kills and deaths do not nearly explain as much as smart kills and worthless deaths. Our approach offers applications for other eSports and traditional sports. All the code is open-sourced.
Highlights
How much does an individual’s performance contribute to a team’s likelihood of winning?This is a central question of sports analytics for traditional sports as well as eSports
How much does an individual contribute to a team’s performance? We find that individual actions conditioned on changes to estimated win probability correlate almost perfectly to team performance: regular kills and deaths do not nearly explain as much as smart kills and worthless deaths
Using a combination of computer vision, dynamic client hooks, machine learning, visualization, logistic regression, large-scale cloud computing, and fast and frugal tree (FFT), we generated new and unique data on millions of League of Legends (LoL) games, calibrated a win probability model, developed enhanced definitions for standard metrics, presented automated improvement analysis, provided a framework for determining an individual’s contribution to a team’s victory, and applied that framework to show that the advanced stats both better correlate with and explain team outcomes
Summary
This is a central question of sports analytics for traditional sports as well as eSports. Like points scored or defended in traditional team sports, eSports measure kills and deaths. Again like traditional team sports, these standard metrics do not do a great job of predicting team performance. There are not that many games to analyze in traditional sports. ESports, is different; millions of games are played every day. League of Legends (LoL), the most-played multiplayer online battle arena (MOBA) game, only has boxscoreequivalent statistics provided by the game’s publisher (Riot Games) through their free application programming interface (API, c.f. Riot Games 2018): e.g., when each champion died, or got a kill or an assist, or similar. All current LoL analytics from amateurs to pros rely on this rudimentary API data
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
