The Impact of COVID-19 on Online Games: Machine Learning and Difference-in-Difference

Shuangyan Wu, Haoran Hu, Yufan Zheng, Qiaoling Zhen, Shuntao Zhang, Choujun Zhan

Abstract: By intervening in people’s behavior, governments in several nations have established a variety of strategies to slow down the spread of COVID-19 pandemic. At the same time, it has a different impact on everyone. Data from the Steam platform online games between January 2018 and February 2021 was used for this project’s analysis. Through the difference-in-difference model in Synthetic Control Methods to quantify and analyze, crucial positive effect on Steam’s online players during COVID-19 and the increase of the number of online players and the released games of the platform in 2020 had been found. The machine learning prediction model was created using the daily totals of the online gaming players of the most popular games on the site. The Ridge regression, whose R squared reached 0.805, had been demonstrated by the experimental results that it got the best performance. Simultaneously, this work found the features of the COVID-19 pandemic and the features of the human mobility, which helps to build a great majority of the predictive models.