lancet-header

Preprints with The Lancet is part of SSRN´s First Look, a place where journals identify content of interest prior to publication. Authors have opted in at submission to The Lancet family of journals to post their preprints on Preprints with The Lancet. The usual SSRN checks and a Lancet-specific check for appropriateness and transparency have been applied. Preprints available here are not Lancet publications or necessarily under review with a Lancet journal. These preprints are early stage research papers that have not been peer-reviewed. The findings should not be used for clinical or public health decision making and should not be presented to a lay audience without highlighting that they are preliminary and have not been peer-reviewed. For more information on this collaboration, see the comments published in The Lancet about the trial period, and our decision to make this a permanent offering, or visit The Lancet´s FAQ page, and for any feedback please contact preprints@lancet.com.

Daily Tracking and Forecasting of the Global COVID-19 Pandemic Trend Using Holt–Winters Exponential Smoothing

190 Pages Posted: 15 Apr 2020

See all articles by Zhanduo Zhang

Zhanduo Zhang

No 989 Hospital of PLA

Xiaona Wang

No 989 Hospital of PLA

Hui Gong

No 989 Hospital of PLA

Xin Liu

No 989 Hospital of PLA

Huijuan Chen

No 989 Hospital of PLA

Zhiliang Chu

No 989 Hospital of PLA

Yubing Guo

No 989 Hospital of PLA

Zheng Chen

No 989 Hospital of PLA

Chunfang Gao

Government of the People's Republic of China - Department of Laboratory Medicine; No 989 Hospital of PLA

Zhongyu Liu

No 989 Hospital of PLA

More...

Abstract

Background: In December 2019, a new coronavirus disease 2019 (COVID-19) outbreak originated from a seafood market in Wuhan, China. The virus, also known as SARS-CoV-2, can transmit quickly between people, and spread globally in just a few months. To contain its spread, the Chinese government adopted a series of comprehensive, rigorous, and thorough prevention and control measures. However, to some extent, it will impact economic fields and social development. Here, we sought to design a prediction model to roughly forecast the peak and inflection points of this epidemic to inform decision making.

Methods: We collected daily COVID-19 data from three sources, including (1) the National Health Commission of the People's Republic of China; (2) health commissions of each province in China; and (3) the World Health Organization’s Situation reports. We used Holt–Winters exponential smoothing to model and predict the global COVID-19 pandemic trend in each city in Hubei, each province in China, and in each country and region where COVID-19 has spread outside China. The Ljung-Box test was used for estimation. All data and analysis results will be updated every day until the pandemic is over.

Findings: We present the first global COVID-19 pandemic predication model. The trend curve, the prediction graph in the next 14 days and the graph reflecting prediction VS real in the last 7 days are updated every day using the number of cases in each region on the designated website (https://2019-ncov-forecast.com/). By observing these charts, the pandemic situation in various countries and regions can be predicted in advance.

Interpretation: As long as the control of epidemic prevention in a certain area is stable and the data is reliable, the prediction accuracy is very high. However, individual regional data are too small to predict, and there are data subject to the fluctuations of local control policies. Further, the prediction errors are not too precise. Our predictions will help to better understand the global COVID-19 trend and to inform decisions to correctly face the tremendous challenges of the pandemic.

Funding Statement: This project is supported by the 989 Hospital Special Fund to Fight the pandemic COVID-19.

Declaration of Interests: None.

Keywords: Coronavirus Disease 2019 (COVID-19); pandemic; modeling prediction; Holt-Winters Exponential Smoothing; Ljung-Box test for estimation

Suggested Citation

Zhang, Zhanduo and Wang, Xiaona and Gong, Hui and Liu, Xin and Chen, Huijuan and Chu, Zhiliang and Guo, Yubing and Chen, Zheng and Gao, Chunfang and Liu, Zhongyu, Daily Tracking and Forecasting of the Global COVID-19 Pandemic Trend Using Holt–Winters Exponential Smoothing (3/27/2020). Available at SSRN: https://ssrn.com/abstract=3564413 or http://dx.doi.org/10.2139/ssrn.3564413

Zhanduo Zhang

No 989 Hospital of PLA

China

Xiaona Wang

No 989 Hospital of PLA

China

Hui Gong

No 989 Hospital of PLA

China

Xin Liu

No 989 Hospital of PLA

China

Huijuan Chen

No 989 Hospital of PLA

China

Zhiliang Chu

No 989 Hospital of PLA

China

Yubing Guo

No 989 Hospital of PLA

China

Zheng Chen

No 989 Hospital of PLA

China

Chunfang Gao

Government of the People's Republic of China - Department of Laboratory Medicine ( email )

Shanghai
China

No 989 Hospital of PLA

China

Zhongyu Liu (Contact Author)

No 989 Hospital of PLA ( email )

China

Click here to go to TheLancet.com

Paper statistics

Abstract Views
1,382
Downloads
141
PlumX Metrics