In this study, we utilized a random forest model to predict the “L” train’s daily ridership in the Chicago downtown area during the pandemic based on environmental, transportation, and COVID-19-related factors. The results indicated that the model accurately predicts ridership one month in advance. However, its accuracy degraded over time. Moreover, average temperature, stay-at-home order status, and percentage of home renters were found to be the most important factors contributing to ridership.
