Vast 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.

中文翻译：

---

明智的杀戮和毫无价值的死亡：《英雄联盟》的电子竞技分析

电子竞技中的大量数据应该易于访问，但通常不是。英雄联盟（LoL）仅具有基本的统计数据，例如等级，物品，金币和死亡人数。我们提出了一种捕获更多有用数据的新方法。我们每秒会多次跟踪每个冠军的位置。我们跟踪所有施放和攻击的能力，造成和避免的所有伤害，视野，健康，法力和冷却时间。我们可以连续，不可见地，远程地，实时地进行跟踪。结合计算机视觉，动态客户端挂钩，机器学习，可视化，逻辑回归，大规模云计算以及快速节俭的树的组合，我们在数百万排名的LoL游戏中生成了这种新的高频数据，从而对游戏获胜概率模型，为标准指标制定增强的定义，引入更多高级指标，自动进行球员改进分析，并在基本和高级统计数据上应用新的球员评估框架。个人对团队的表现有多大贡献？我们发现，以估计获胜概率的变化为条件的个人行动几乎与团队绩效密切相关：常规的杀戮和死亡并不能解释为聪明的杀戮和毫无价值的死亡。我们的方法为其他电子竞技和传统运动提供了应用。所有代码都是开源的。定期的杀戮和死亡几乎不能解释聪明的杀戮和毫无价值的死亡。我们的方法为其他电子竞技和传统运动提供了应用。所有代码都是开源的。定期的杀戮和死亡几乎不能解释聪明的杀戮和毫无价值的死亡。我们的方法为其他电子竞技和传统运动提供了应用。所有代码都是开源的。