A Comparison of Methods for Player Clustering via Behavioral Telemetry

TL;DR

This paper compares various unsupervised clustering methods, including Archetypal Analysis, to categorize player behavior in World of Warcraft using five years of telemetry data, aiming to produce actionable profiles.

Contribution

It introduces a comprehensive evaluation of multiple clustering techniques, including Archetypal Analysis, for deriving meaningful player behavior profiles from complex telemetry data.

Findings

Archetypal Analysis effectively identifies interpretable player behavior archetypes.

Different clustering methods vary in their ability to produce actionable profiles.

The study provides insights into the strengths and limitations of each technique for game telemetry data.

Abstract

The analysis of user behavior in digital games has been aided by the introduction of user telemetry in game development, which provides unprecedented access to quantitative data on user behavior from the installed game clients of the entire population of players. Player behavior telemetry datasets can be exceptionally complex, with features recorded for a varying population of users over a temporal segment that can reach years in duration. Categorization of behaviors, whether through descriptive methods (e.g. segmention) or unsupervised/supervised learning techniques, is valuable for finding patterns in the behavioral data, and developing profiles that are actionable to game developers. There are numerous methods for unsupervised clustering of user behavior, e.g. k-means/c-means, Non-negative Matrix Factorization, or Principal Component Analysis. Although all yield behavior categorizations, interpretation of the resulting categories in terms of actual play behavior can be difficult if not impossible. In this paper, a range of unsupervised techniques are applied together with Archetypal Analysis to develop behavioral clusters from playtime data of 70,014 World of Warcraft players, covering a five year interval. The techniques are evaluated with respect to their ability to develop actionable behavioral profiles from the dataset.