Nowcasting of COVID-19 Confirmed Cases: Foundations, Trends, and Challenges

ABSTRACT

The coronavirus disease 2019 (COVID-19) has become a public health emergency of international concern affecting more than 200 countries and territories worldwide. As of September 30, 2020, it has caused a pandemic outbreak with more than 33 million confirmed infections, and more than 1 million reported deaths worldwide. Several statistical, machine learning, and hybrid models have previously been applied to forecast COVID-19 confirmed cases for profoundly affected countries. Future predictions of daily COVID-19 cases are useful for the effective allocation of healthcare resources and will act as an early-warning system for government policymakers. However, due to the presence of extreme uncertainty in these time series datasets, forecasting of COVID-19 confirmed cases has become a very challenging job. For univariate time series forecasting, there are various statistical and machine learning models available in the literature. Still, nowcasting and forecasting of COVID-19 cases are difficult due to insufficient input data, flaw in modeling assumptions, lack of epidemiological features, inadequate past evidence on effects of available interventions, and lack of transparency. This chapter focuses on assessing different short-term forecasting models that are popularly used to forecast the daily COVID-19 cases for various countries. This chapter provides strong empirical evidence that there is no universal method available that can accurately forecast pandemic data. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.