Comparison of some forecasting methods for COVID-19

Abstract

In this paper, we use forecasting methods such as Euler’s iterative method and cubic spline interpolation to predict the total number of people infected and the number of active cases for COVID-19 propagation. We construct a novel iterative method, which is based on cubic spline interpolation and Euler’s method and it is an improvement over the two latter methods. The novel method is very efficient for forecasting and to describe the underlying dynamics of the pandemic. Our predicted results are also compared with an iterative method developed by Perc et al. (2020) [1]. Our study encompasses the following countries namely; South Korea, India, South Africa, Germany, and Italy. We use data from 15 February 2020 to 31 May 2020 in order to obtain graphs and then obtain predicted values as from 01 June 2020. We use two criteria to classify whether the predicted value for a certain day is effective or not.