Theta autoregressive neural network model for COVID-19 outbreak predictions

CHAKRABORTY, T.; Bhattacharyya, A.; Pattnaik, M.

An unprecedented outbreak of the novel coronavirus (COVID-19) in the form of peculiar pneumonia has spread globally since its first case at Wuhan, China, in December 2019, increasing infected cases and mortality at a pandemic speed. Thus, forecasting the COVID-19 pandemic became a key research interest for both the epidemiologists and statisticians. These future predictions are useful for the effective allocation of health care resources, stockpiling, and help in strategic planning for clinicians, government authorities, and public-health policymakers after understanding the extent of the effect. The main objective of this paper is to develop the most suitable forecasting model that can generate real-time short-term (ten days) and long-term (fifty days) out-of-sample forecasts of COVID-19 outbreaks for eight profoundly affected countries, namely the United States of America, Brazil, India, Russia, South Africa, Mexico, Spain, and Iran. A novel hybrid approach based on the Theta model and Autoregressive neural network (ARNN) model, named Theta-ARNN (TARNN) model, is proposed. The proposed method outperforms previously available single and hybrid forecasting models for COVID-19 predictions in most data sets. In addition, the ergodicity and asymptotic stationarity of the proposed TARNN model are established which is of particular interest in nonlinear time series literature.