基于 Plus/Minus 值的 Counter-Strike: Global Offensive 选手评分
Rating Players of Counter-Strike: Global Offensive Based on Plus/Minus value
AI总结：
本文提出基于 Plus/Minus 值的 CS 选手评分机制，利用回归与贝叶斯模型衡量选手对战队分差的直接及间接贡献，以弥补 Rating 2.0 只重个人表现的不足。
摘要：
我们通过分析选手的 Plus/Minus 值，为热门电子竞技项目 Counter-Strike: Global Offensive（CS）提出了一种选手评分机制。Plus/Minus 值表示在选手参加的所有比赛中，其所在战队与对手战队之间的平均分差。我们使用正则化线性回归、逻辑回归和贝叶斯线性模型等模型，考察选手参赛与战队分差之间的关系。CS 社区最常用的指标是“Rating 2.0”，它只关注个人表现，没有考虑对战队成功的间接贡献。我们的方法引入了一种新的评分系统，用于评估选手的直接和间接贡献，并优先考虑那些对比赛结果产生切实影响的选手，而不是个人得分最高的选手。该评分系统可以帮助战队更公平地分配奖励，并改进选手招募。我们相信，这一方法不仅会对 CS 社区产生积极影响，也会惠及更广泛的电子竞技行业。
英文摘要：
We propose a player rating mechanism for Counter-Strike: Global Offensive (CS ), a popular e-sport, by analyzing players' Plus/Minus values. The Plus/Minus value represents the average point difference between a player's team and the opponent's team across all matches the player has participated in. Using models such as regularized linear regression, logistic regression, and Bayesian linear models, we examine the relationship between player participation and team point differences. The most commonly used metric in the CS community is "Rating 2.0," which focuses solely on individual performance and does not account for indirect contributions to team success. Our approach introduces a new rating system that evaluates both direct and indirect contributions of players, prioritizing those who make a tangible impact on match outcomes rather than those with the highest individual scores. This rating system could help teams distribute rewards more fairly and improve player recruitment. We believe this methodology will positively influence not only the CS community but also the broader e-sports industry.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
