COVID-19’s Impact on the Box office: Machine Learning and Difference-in-Difference

Abstract

As COVID-19 continues to spread around the world, and non-pharmacological interventions (NPIs) continue to be strengthened, the impact of COVID-19 on the film industry has not yet been clearly quantified. In this study, the Difference-in-Difference model is used to quantify the impact of the COVID-19 pandemic on the box office. Results indicate that the COVID-19 pandemic has a significant negative effect on the daily global box office. Additionally, based on a research dataset containing information on movies and COVID-19, ten machine learning methods were used to build a prediction model of the cumulative global box office. The experimental results showed that Extremely Randomized Trees had the best predictive performance, and it was found that COVID-19 features helped improve the predictive performance of several models.