Analytics-Driven Dynamic Game Adaption for Player Retention in a 2-Dimensional Adventure Game

Abstract

This paper shows how game analytics can be used to dynamically adapt a casual, 2-D adventure game named Sidequest: The Game (SQ:TG) in order to increase session-level retention. Our technique involves using game analytics to create an abstracted game analytic space to make the problem tractable. We then model player retention in this space and move through this space in accordance to a target distribution of game states in order to influence player behavior. Experiments performed show that the adaptive version of SQ:TG is able to better fit a target distribution of game states while also significantly reducing the quitting rate compared to the non-adaptive version of the game.