Predictive Analysis Based on Prophet Model: Evidence from the Number of Epidemic Infections

Jiachen Pan; Zitong Xu

doi:10.54097/ezc7h416

Authors

Jiachen Pan
Zitong Xu

DOI:

https://doi.org/10.54097/ezc7h416

Keywords:

Prophet, ARIMA, ETS, GARCH, Forecasting, Correlation

Abstract

This study makes a prediction of infection numbers in the future and investigates the correlation between the new cases and the stock price of companies in three different fields. In the first part of the prediction, we use three methods to make predictions of the future infected number, including the ETS, Auto-Regressive Moving Average (ARIMA), and Prophet model. In the next part, we use the GARCH model to discuss the correlation between infection numbers and stock prices. Considering the heterogeneity, we choose three different companies’ stocks to represent three industries respectively. They are Apple, Amazon and Pfizer. The result indicates that the stock price of Apple is negatively correlated to the infection number, the relationship between the infection number and the price of Amazon is inconspicuous, while the price of Pfizer is positively correlated with the development of the pandemic. Thus, we draw the conclusion that the impact of the epidemic is strong to manufacturing, is not obvious to the Internet industry, and boosts the development of the medical corporation.

Downloads

Download data is not yet available.

References

Battineni, G., Chintalapudi, N. and Amenta, F. Forecasting of covid-19 epidemic size in four high hitting nations (USA, Brazil, India and Russia) by FB-Prophet Machine Learning Model, Applied Computing and Informatics ,2020.

Tulshyan, V., Sharma, D. and Mittal, M. An eye on the future of covid-19: Prediction of likely positive cases and fatality in India over a 30-day horizon using the Prophet Model, Disaster Medicine and Public Health Preparedness, 2020, 16(3), 980–986.

Sardar, I. et al. Machine Learning and Automatic Arima/prophet models-based forecasting of COVID-19: Methodology, evaluation, and case study in SAARC countries, Stochastic Environmental Research and Risk Assessment, 2022, 37(1), 345–359.

Alghamdi, S. et al. Using fuzzy time series forecasting and gaussian mixture model to classify and predict new cases of COVID-19 in Saudi Arabia, Thermal Science,2022, 26(1), 261–270.

Makarovskikh T .System for Forecasting COVID-19 Cases Using Time-Series and Neural Networks Models.Engineering Proceedings, 2021, 5.

Gull, K., Kanakaraddi, S. and Chikaraddi, A. Covid-19 outbreak prediction using additive time series forecasting model, Trends in Sciences, 2022,19(22), 1919.

Jinguan Lin, Yizhi Mao, Hongxia Hao. Realized GARCH Models with Time-Varying Leverage Effects. 2023.

Zhiqiang Hu. Research on the linkage between China and the United States stock market based on the DCC-GARCH model. 2022.

Abdullah, A.M. The impact of covid-19 and the Russia–Ukraine conflict on the relationship between the US islamic stock index, Bitcoin, and Commodities, Asian Economics Letters, 2023, 4(2).

Jamil, I. et al. Pre- and post-covid-19: The impact of US, UK, and European Stock Markets on ASEAN-5 Stock Markets, International Journal of Financial Studies, 2023,11(2), 54.

Chen, J. et al. The impact of covid-19 on the US oil stock market and currency, Advances in Economics, Management and Political Sciences, 2023, 3(1),182–191.

Zhao, J. The long-term impact of covid-19 on US Stock Market: Evidence from Time Series model, BCP Business & Management, 2023, 38, 1476–1484.

Taylor, S.J. and Letham, B. Forecasting at scale, PeerJ Preprints. Available at: https://peerj.com/preprints/3190/, 2017.