Difficulty Modelling in Mobile Puzzle Games: An Empirical Study on Different Methods to Combine Player Analytics and Simulated Data
This addresses the challenge for game developers in optimizing player engagement by predicting difficulty pre-release, though it is incremental as it builds on existing data combination techniques.
The study tackled the problem of estimating difficulty in mobile puzzle games before release by comparing methods that combine player analytics and simulated data, finding that models using both cohort statistics and simulations were most accurate, with artificial neural networks performing most consistently.
Difficulty is one of the key drivers of player engagement and it is often one of 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 player interactions with the content; however, this allows for estimation only after the content is released and does not consider the characteristics of potential future players. In this article, we present a number of potential solutions for the estimation of difficulty under such conditions, and we showcase the results of a comparative study intended to understand which method and which types of data perform better in different scenarios. The results reveal that models trained on a combination of cohort statistics and simulated data produce the most accurate estimations of difficulty in all scenarios. Furthermore, among these models, artificial neural networks show the most consistent results.