PROJECT TITLE :

Clustering Game Behavior Data

ABSTRACT:

Recent years have seen a deluge of behavioral information from players hitting the game business. Reasons for this information surge are several and embrace the introduction of new business models, technical innovations, the recognition of online games, and the increasing persistence of games. No matter the causes, the proliferation of behavioral information poses the matter of the way to derive insights therefrom. Behavioral data sets can be massive, time-dependent and high-dimensional. Clustering offers a way to explore such data and to get patterns that may scale back the general complexity of the info. Clustering and alternative techniques for player profiling and play style analysis have, so, become well-liked within the nascent field of game analytics. But, the proper use of clustering techniques needs expertise and an understanding of games is important to evaluate results. With this paper, we have a tendency to address game knowledge scientists and gift a review and tutorial that specialize in the application of clustering techniques to mine behavioral game data. Several algorithms are reviewed and samples of their application shown. Key topics like feature normalization are discussed and open problems within the context of game analytics are noticed.