Guns, swords and data: Clustering of player behavior in computer games in the wild

Abstract

Behavioral data from computer games can be exceptionally high-dimensional, of massive scale and cover a temporal segment reaching years of real-time and a varying population of users. Clustering of user behavior provides a way to discover behavioral patterns that are actionable for game developers. Interpretability and reliability of clustering results is vital, as decisions based on them affect game design and thus ultimately revenue. Here case studies are presented focusing on clustering analysis applied to high-dimensionality player behavior telemetry, covering a combined total of 260,000 characters from two major commercial game titles: the Massively Multiplayer Online Role-Playing Game Tera and the multi-player strategy war game Battlefield 2: Bad Company 2. K-means and Simplex Volume Maximization clustering were applied to the two datasets, combined with considerations of the design of the games, resulting in actionable behavioral profiles. Depending on the algori thm different insights into the underlying behavior of the population of the two games are provided

Player Preference and Style in a Leading Mobile Card Game

“…Previous work has found different player types in many games using various methods of clustering [25], [26], [27]. Decision trees, as demonstrated in this paper, are a suitable representation of play style and could help with the understanding of the differences between these player types due to the ease of comparing their human readable model.…”

Game user telemetry in practice

“…Unfortunately, case studies of academic-industry partnerships in the area of user-oriented research are still sparse, as details about telemetry data and analysis methods are usually considered confidential by game developers (see, e.g., [4]). Among the available studies, Lameman et al [8] highlighted the importance of game industry-academic relationships and discussed the process and results from a collaboration between Simon Fraser University and Bardel Entertainment to develop new user testing methods.…”

Classification of Player Roles in the Team-Based Multi-player Game Dota 2

“…An approach to ML in computer games in general was proposed by Drachen et al [2]. They suggest using unsupervised learning algorithms, specifically k-means and Simplex Volume Maximization, to cluster player behavioral data.…”