A Machine Learning Model for Nowcasting Epidemic Incidence

TL;DR

This paper presents a simple random forest model for nowcasting COVID-19 incidence counts, effectively estimating real-time infection numbers despite reporting delays, and compares favorably to complex Bayesian methods.

Contribution

Introduces a straightforward random forest approach for epidemic nowcasting that outperforms complex Bayesian models in accuracy and efficiency.

Findings

Random forest model provides accurate nowcasts of COVID-19 incidence.

Model performs well with simple covariates like reported counts and day of week.

Method is computationally efficient and compares favorably to hierarchical Bayesian models.

Abstract

Due to delay in reporting, the daily national and statewide COVID-19 incidence counts are often unreliable and need to be estimated from recent data. This process is known in economics as nowcasting. We describe in this paper a simple random forest statistical model for nowcasting the COVID - 19 daily new infection counts based on historic data along with a set of simple covariates, such as the currently reported infection counts, day of the week, and time since first reporting. We apply the model to adjust the daily infection counts in Ohio, and show that the predictions from this simple data-driven method compare favorably both in quality and computational burden to those obtained from the state-of-the-art hierarchical Bayesian model employing a complex statistical algorithm.