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.
Reference56 articles.
1. Gaming market - growth trends COVID-19 impact and forecasts (2022-2027) https://www.mordorintelligence.com/industry-reports/global-gaming-market.
2. Global games market to generate $175.8 billion in 2021; despite a slight decline the market is on track to surpass $200 billion in 2023 https://newzoo.com/insights/articles/global-games-market-to-generate-175-8-billion-in-2021-despite-a-slight-decline-the-market-is-on-track-tosurpass-200-billion-in-2023/.
3. How much is the gaming industry worth in 2022? (revenue &stats) https://earthweb.com/how-much-is-the-gaming-industry-worth/.
4. KristensenJ. GuckelsbergerC. BurelliP. andHämäläinenP. Personalized game difficulty prediction using factorization machines Proceedings of the 35th Annual ACM Symposium on User Interface Software and Technology 2022 Bend OR USA https://doi.org/10.1145/3526113.3545624.