Title: A tuned Holt-Winters white-box model for COVID-19 prediction

Authors: Seng Hansun; Vincent Charles; Tatiana Gherman; Subanar; Christiana Rini Indrati

Addresses: Informatics Department, Universitas Multimedia Nusantara, Tangerang, Indonesia ' School of Management, University of Bradford, Bradford BD7 1DP, UK ' Faculty of Business and Law, University of Northampton, Northampton NN1 5PH, UK ' Faculty of Mathematics and Natural Science, Universitas Gadjah Mada, Yogyakarta, Indonesia ' Faculty of Mathematics and Natural Science, Universitas Gadjah Mada, Yogyakarta, Indonesia

Abstract: The year 2020 has become memorable the moment the novel COVID-19 spread massively around the world to become a pandemic. In this paper, we analyse and predict the future trend of the COVID-19 cases for the top ten countries with the highest number of confirmed cases to date and the top ten countries with the highest growth percentage within the last month. Since many recent works have proposed that the COVID-19 pattern follows an exponential distribution, we use a tuned approach to the Holt-Winters' additive method as a white-box model. Based on the analysis, we found that most of the countries are still presenting an increasing trend of confirmed cases in the near future. Apart from vaccine and drug development, measures such as vigilance, strategic governmental actions, public awareness, and social distancing are unarguably continuously needed to handle the spreading of COVID-19 and avoid or curb the next wave of the outbreak.

Keywords: COVID-19; future wave; Holt-Winters additive method; prediction; white-box model.

DOI: 10.1504/IJMDM.2021.116018

International Journal of Management and Decision Making, 2021 Vol.20 No.3, pp.241 - 262

Received: 16 Jul 2020
Accepted: 01 Aug 2020
Published online: 06 Jul 2021 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article