This article describes an attempt to categorize character configurations of players of Tom Clancy's the Division 2, conducted to highlight behavioral differences in approach to gameplay based on one's character build. Nine distinct character builds were extracted for maximum coherence and minimum variance and each build showed significant differences in separate measures of behavior such as playtime, character health and armor among other attributes. The proposed method was also able to recover builds recognized by social forums as well as discovering new ones. Appropriation of Character builds as categorical text-based data (BaT: Build as Text), provides a unique opportunity for game researchers to use a diverse set of input data which will in turn contribute to the improvement of the process of game design informed by player choices. Longitudinal observations in interconnection of obtained clusters may provide further insight into formation and evolution of gameplay types.

Anomaly detection in an industrial context is a complex task. Despite very large amounts of available data, only a small fraction is labelled and anomalies are often of different nature. Moreover, implementing anomaly detection algorithms in a production environment is a costly task, therefore it is needed to unambiguously rank candidate algorithms beforehand. In this paper, we propose a methodological pipeline to evaluate anomaly detection algorithms performance in the presence of very few positive labelled data, belonging to different positive types, within an industrial context. In this pipeline, called BRIGADE (BenchmaRkInG Anomaly DEtection algorithms), we first build multiple benchmarking datasets from the limited available labelled positives and unlabelled production data. Then, we train and test candidate algorithms using a repeated 2-fold cross-validation technique. To evaluate the results, we use a metric usually employed for ranked retrieval tasks. We then aggregate all the results obtained for different benchmarking datasets into a single ranking of the candidate algorithms. We present results obtained with real industrial data, showing exposure to genuine anomalies and demonstrate cost savings.