Application of Machine Learning Techniques for Epidemic Forecasting

4 Pages Posted: 7 Oct 2020 Last revised: 4 Jan 2021

See all articles by Jyotsna Jayaraj

Jyotsna Jayaraj

Amity University, Mumbai

Siddhartha Dutta

Amity University, Mumbai

Date Written: June 26, 2020


Infectious diseases such as H1N1, SARS, Zika, and the recent COVID-19 continue to pose a global threat. It is crucial to characterize diseases and their dynamics, in order to understand an ongoing epidemic efficiently. This paper discusses two existent models of prediction for outbreak and severity that helps understand how machine learning algorithms can facilitate accurate predictions of epidemics and their related patterns, consequently influencing decisions to contain its spread. This paper implements an extrapolating model that demonstrates the proposed system using associated data from the COVID-19 epidemic. The model uses time series forecasting to predict the future number of confirmed cases using current trends in the data. The future scope discusses the uses of other machine learning techniques to discern epidemiological trends.

Keywords: epidemiology, machine learning, outbreak prediction, time series forecasting, coronavirus disease

Suggested Citation

Jayaraj, Jyotsna and Dutta, Siddhartha, Application of Machine Learning Techniques for Epidemic Forecasting (June 26, 2020). Proceedings of the International Conference on Recent Advances in Computational Techniques (IC-RACT) 2020, Available at SSRN: or

Jyotsna Jayaraj (Contact Author)

Amity University, Mumbai ( email )

Siddhartha Dutta

Amity University, Mumbai ( email )

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Abstract Views
PlumX Metrics