Using Recommendation Systems to Adapt Gameplay

Abstract

Recommendation systems are key components in many Web applications (Amazon, Netflix, eHarmony). Each system gathers user input, such as the products they buy, and searches for patterns in order to determine user preferences and tastes. These preferences are then used to recommend other content that a user may enjoy. Games on the other hand are often designed with a one-size-fits-all approach not taking player preferences into account. However there is a growing interest in both the games industry and game research communities to begin incorporating systems that can adapt, or alter how the game functions, to specific players. This paper examines how Web application recommendation systems compare to current games that adapt their gameplay to specific players. The comparison shows that current games do not use recommendation methods that are data intensive or collaborative when adapting to players. Design suggestions are offered within this manuscript for how game developers can benefit from incorporating the lesser used recommendation methods.