Comparing the accuracy of several network-based COVID-19 prediction algorithms

Massimo A. Achterberg; Bastian Prasse; Long Ma; Stojan Trajanovski; Maksim Kitsak; Piet Van Mieghem

doi:10.1016/j.ijforecast.2020.10.001

Comparing the accuracy of several network-based COVID-19 prediction algorithms

Massimo A. Achterberg^*, Bastian Prasse, Long Ma, Stojan Trajanovski, Maksim Kitsak, Piet Van Mieghem

^*Corresponding author for this work

Network Architectures and Services

Research output: Contribution to journal › Article › Scientific › peer-review

26 Citations (Scopus)

107 Downloads (Pure)

Abstract

Researchers from various scientific disciplines have attempted to forecast the spread of coronavirus disease 2019 (COVID-19). The proposed epidemic prediction methods range from basic curve fitting methods and traffic interaction models to machine-learning approaches. If we combine all these approaches, we obtain the Network Inference-based Prediction Algorithm (NIPA). In this paper, we analyse a diverse set of COVID-19 forecast algorithms, including several modifications of NIPA. Among the algorithms that we evaluated, the original NIPA performed best at forecasting the spread of COVID-19 in Hubei, China and in the Netherlands. In particular, we show that network-based forecasting is superior to any other forecasting algorithm.

Original language	English
Pages (from-to)	489-504
Number of pages	16
Journal	International Journal of Forecasting
Volume	38
Issue number	2
DOIs	https://doi.org/10.1016/j.ijforecast.2020.10.001
Publication status	Published - 2022

Keywords

Bayesian methods
Epidemiology
Forecast accuracy
Machine learning methods
Network inference
SIR model
Time series methods

Access to Document

10.1016/j.ijforecast.2020.10.001

1-s2.0-S0169207020301552-mainFinal published version, 2.13 MBLicence: CC BY

Cite this

@article{7ba0eba48dc54e1aa716ed9c6fa149e4,

title = "Comparing the accuracy of several network-based COVID-19 prediction algorithms",

abstract = "Researchers from various scientific disciplines have attempted to forecast the spread of coronavirus disease 2019 (COVID-19). The proposed epidemic prediction methods range from basic curve fitting methods and traffic interaction models to machine-learning approaches. If we combine all these approaches, we obtain the Network Inference-based Prediction Algorithm (NIPA). In this paper, we analyse a diverse set of COVID-19 forecast algorithms, including several modifications of NIPA. Among the algorithms that we evaluated, the original NIPA performed best at forecasting the spread of COVID-19 in Hubei, China and in the Netherlands. In particular, we show that network-based forecasting is superior to any other forecasting algorithm.",

keywords = "Bayesian methods, Epidemiology, Forecast accuracy, Machine learning methods, Network inference, SIR model, Time series methods",

author = "Achterberg, {Massimo A.} and Bastian Prasse and Long Ma and Stojan Trajanovski and Maksim Kitsak and {Van Mieghem}, Piet",

year = "2022",

doi = "10.1016/j.ijforecast.2020.10.001",

language = "English",

volume = "38",

pages = "489--504",

journal = "International Journal of Forecasting",

issn = "0169-2070",

publisher = "Elsevier",

number = "2",

}

TY - JOUR

T1 - Comparing the accuracy of several network-based COVID-19 prediction algorithms

AU - Achterberg, Massimo A.

AU - Prasse, Bastian

AU - Ma, Long

AU - Trajanovski, Stojan

AU - Kitsak, Maksim

AU - Van Mieghem, Piet

PY - 2022

Y1 - 2022

N2 - Researchers from various scientific disciplines have attempted to forecast the spread of coronavirus disease 2019 (COVID-19). The proposed epidemic prediction methods range from basic curve fitting methods and traffic interaction models to machine-learning approaches. If we combine all these approaches, we obtain the Network Inference-based Prediction Algorithm (NIPA). In this paper, we analyse a diverse set of COVID-19 forecast algorithms, including several modifications of NIPA. Among the algorithms that we evaluated, the original NIPA performed best at forecasting the spread of COVID-19 in Hubei, China and in the Netherlands. In particular, we show that network-based forecasting is superior to any other forecasting algorithm.

AB - Researchers from various scientific disciplines have attempted to forecast the spread of coronavirus disease 2019 (COVID-19). The proposed epidemic prediction methods range from basic curve fitting methods and traffic interaction models to machine-learning approaches. If we combine all these approaches, we obtain the Network Inference-based Prediction Algorithm (NIPA). In this paper, we analyse a diverse set of COVID-19 forecast algorithms, including several modifications of NIPA. Among the algorithms that we evaluated, the original NIPA performed best at forecasting the spread of COVID-19 in Hubei, China and in the Netherlands. In particular, we show that network-based forecasting is superior to any other forecasting algorithm.

KW - Bayesian methods

KW - Epidemiology

KW - Forecast accuracy

KW - Machine learning methods

KW - Network inference

KW - SIR model

KW - Time series methods

UR - http://www.scopus.com/inward/record.url?scp=85094925562&partnerID=8YFLogxK

U2 - 10.1016/j.ijforecast.2020.10.001

DO - 10.1016/j.ijforecast.2020.10.001

M3 - Article

AN - SCOPUS:85094925562

SN - 0169-2070

VL - 38

SP - 489

EP - 504

JO - International Journal of Forecasting

JF - International Journal of Forecasting

IS - 2

ER -

Comparing the accuracy of several network-based COVID-19 prediction algorithms

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this