Individualized Context-Aware Tensor Factorization for Online Games Predictions
This addresses the problem of personalized prediction in multiplayer online games for game developers and players, but it is incremental as it builds on existing tensor factorization methods with individualization.
The paper tackled predicting user performance and game outcomes in online games by modeling individualized context-aware behavior, and demonstrated substantial improvements in predicting winning outcomes, individual performance, and engagement using a dataset from League of Legends.
Individual behavior and decisions are substantially influenced by their contexts, such as location, environment, and time. Changes along these dimensions can be readily observed in Multiplayer Online Battle Arena games (MOBA), where players face different in-game settings for each match and are subject to frequent game patches. Existing methods utilizing contextual information generalize the effect of a context over the entire population, but contextual information tailored to each individual can be more effective. To achieve this, we present the Neural Individualized Context-aware Embeddings (NICE) model for predicting user performance and game outcomes. Our proposed method identifies individual behavioral differences in different contexts by learning latent representations of users and contexts through non-negative tensor factorization. Using a dataset from the MOBA game League of Legends, we demonstrate that our model substantially improves the prediction of winning outcome, individual user performance, and user engagement.