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

TL;DR

This study compares various methods for estimating game difficulty using player analytics and simulated data, finding that combining cohort statistics with simulations and using neural networks yields the most accurate results.

Contribution

It introduces and empirically evaluates multiple approaches for difficulty modeling in mobile puzzle games, highlighting the effectiveness of combined data and neural networks.

Findings

Models with combined cohort and simulated data outperform others.

Artificial neural networks provide the most consistent difficulty estimations.

Combining different data sources improves estimation accuracy across scenarios.

Abstract

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.