Difficulty Modelling in Mobile Puzzle Games: an Empirical Study on Different Methods to Combine Player Analytics and Simulated Data

Difficulty is one of the key drivers of player engagement and it is often oneof the aspects that designers tweak most to optimise the player experience;operationalising it is, therefore, a crucial task for game development studios.A common practice consists of creating metrics out of data collected by playerinteractions with the content; however, this allows for estimation only afterthe content is released and does not consider the characteristics of potentialfuture players. In this article, we present a number of potential solutions for theestimation of difficulty under such conditions, and we showcase the results ofa comparative study intended to understand which method and which types of dataperform better in different scenarios. The results reveal that models trained on a combination of cohort statisticsand simulated data produce the most accurate estimations of difficulty in allscenarios. Furthermore, among these models, artificial neural networks show themost consistent results.