Valuing Player Actions in Counter-Strike: Global Offensive

11/02/2020
by   Peter Xenopoulos, et al.
16

Esports, despite its expanding interest, lacks fundamental sports analytics resources such as accessible data or proven and reproducible analytical frameworks. Even Counter-Strike: Global Offensive (CSGO), the second most popular esport, suffers from these problems. Thus, quantitative evaluation of CSGO players, a task important to teams, media, bettors and fans, is difficult. To address this, we introduce (1) a data model for CSGO with an open-source implementation; (2) a graph distance measure for defining distances in CSGO; and (3) a context-aware framework to value players' actions based on changes in their team's chances of winning. Using over 70 million in-game CSGO events, we demonstrate our framework's consistency and independence compared to existing valuation frameworks. We also provide use cases demonstrating high-impact play identification and uncertainty estimation.

READ FULL TEXT
research
05/26/2018

Deep Reinforcement Learning in Ice Hockey for Context-Aware Player Evaluation

A variety of machine learning models have been proposed to assess the pe...
research
09/20/2021

Optimal Team Economic Decisions in Counter-Strike

The outputs of win probability models are often used to evaluate player ...
research
02/10/2022

Pokémon GO to Pokémon STAY: How Covid-19 Affected Pokémon GO Players

Since its creation, the Location-Based Game (LBG), Pokémon GO, has been ...
research
02/06/2019

Playing Fast Not Loose: Evaluating team-level pace of play in ice hockey using spatio-temporal possession data

Pace of play is an important characteristic in hockey as well as other t...
research
07/14/2021

GgViz: Accelerating Large-Scale Esports Game Analysis

Game review is crucial for teams, players and media staff in sports. Des...
research
04/25/2020

Aim Low, Shoot High: Evading Aimbot Detectors by Mimicking User Behavior

Current schemes to detect cheating in online games often build on the as...
research
06/03/2021

What Happened Next? Using Deep Learning to Value Defensive Actions in Football Event-Data

Objectively quantifying the value of player actions in football (soccer)...

Please sign up or login with your details

Forgot password? Click here to reset