Preprint Open Access

Forecasting The Spread of COVID-19 with Enhanced Linear Autoregression

Ethan Mann; Quentin Chevalier; Geoffrey Magda; Matthew Gonzalgo

The COVID-19 pandemic is the focal point of global attention in 2020, as the virus has affected most of the world. Effectively responding to the pandemic continues to be a major and urgent issue; as of September 2020, there is still no widely accepted cure for the disease. To complement medical studies regarding the nature of the virus and provide decision-makers with tools to handle the crisis, Caltech offered the Spring 2020 CS156b course to forecast the probability distribution of the number of COVID-19 related deaths. The challenge was held during April and May 2020, and the predictive goal was to model fatalities as reported by the New York Times (NYT) two weeks into the future on the county level, with predictions evaluated via pinball loss. This paper details our team's model submission, a linear autoregressive model with features for cases and fatalities.

Files (1.9 MB)
Name Size
1.9 MB Download
  • Catrin Sohrabi, Zaid Alsafi, Niamh O'Neill, Mehdi Khan, Ahmed Kerwan, Ahmed Al-Jabir, Christos Iosifidis,and Riaz Agha. World health organization declares global emergency: A review of the 2019 novel coronavirus(covid-19).International Journal of Surgery, 76:71 – 76, 2020.

  • Ingo Steinwart and Andreas Christmann. Estimating conditional quantiles with the help of the pinball loss.Bernoulli, 17(1):211–225, 02 2011.

  • J. Contreras, R. Espinola, F. J. Nogales, and A. J. Conejo. Arima models to predict next-day electricity prices.IEEE Transactions on Power Systems, 18(3):1014–1020, 2003.

  • Michael S. Warren and Samuel W. Skillman. Mobility changes in response to covid-19, 2020.

  • Na Zhu, Dingyu Zhang, Wenling Wang, Xingwang Li, Bo Yang, Jingdong Song, Xiang Zhao, Baoying Huang,Weifeng Shi, Roujian Lu, Peihua Niu, Faxian Zhan, Xuejun Ma, Dayan Wang, Wenbo Xu, Guizhen Wu, George F.Gao, and Wenjie Tan. A novel coronavirus from patients with pneumonia in china, 2019.New England Journal ofMedicine, 382(8):727–733, 2020. PMID: 31978945.

  • R. Adhikari and R. Agrawal. An introductory study on time series modeling and forecasting.ArXiv, abs/1302.6613,2013.

All versions This version
Views 495495
Downloads 166166
Data volume 311.9 MB311.9 MB
Unique views 387387
Unique downloads 148148


Cite as