Abstract
During the current global urgency, scientists,
clinicians and healthcare experts around the globe keep on searching for
accurate and reliable COVID-19 forecasting models to support in tackling the
deadly and highly infectious disease. In this research paper, the ANN approach
was applied to analyze COVID-19 daily cases in Azerbaijan. This study is based
on daily new cases of COVID-19 in Azerbaijan for the period 1 January 2020 – 25
March 2021. The out-of-sample forecast covers the period 26 March 2021 – 31
July 2021. The residuals and forecast evaluation criteria (Error, MSE and MAE)
of the applied ANN (12, 12, 1) model indicate that the model is stable in
forecasting daily COVID-19 cases in the country. The results of the study
indicate that that daily COVID-19 cases in Azerbaijan are likely to remain
significantly high over the out-of-sample period. The government of Azerbaijan,
through its ministry of health, should continue to implement COVID-19 control
and prevention measures such as isolation, quarantine, testing and tracing,
face-mask wearing, sanitization of hands and so on, in line with WHO standards.
