№1, 2021


Firangiz I. Sadiyeva

The article proposes an Autoregressive Integrated Moving Average (ARIMA) model to predict the COVID-19 pandemic. COVID-19 is a new type of pandemic that is spreading rapidly around the world and is currently continuing.  Recently, the number of pandemic cases in Azerbaijan has reached the highest rate. For this reason, the forecast of the COVID-19 pandemic is reviewed, and the COVID-19 time series of the ARIMA model proposed in experiments with real data covering several months is used with different parameters for forecasting. According to the data, the number of daily infections officially registered by the Ministry of Healthcare of the Republic of Azerbaijan (www.sehiyye.gov.az) between 22.01.2020 - 22.10.2020 is considered. Using these data, the incidence of infections in our country in the next period is forecasted. For this purpose, various parameters are given to the ARIMA model and the error rate of each model was evaluated accordingly. MAPE (Mean Absolute Percentage Error), MAE (Mean Absolute Error), and RMSE (Root Mean Square Error) functions are used to estimate the error. As a result of comparisons, the most suitable model is selected. The results obtained are an important factor for both the health care system and ordinary citizens during the pandemic in our country. The results confirm that statistical methods can be effective in applying non-stationary coronavirus time-series predictions to other issues (pp.95–104)

Keywords: COVID-19, coronavirus, ARIMA, forecast, time-series.
  • The World Health Organization (WHO). Coronavirus disease (COVID-2019) situation reports. URL: https://www.who.int/emergencies/diseases/novel-coronavirus-2019/situation-reports/
  • Chakraborty T., and Ghosh I. Real-time forecasts and risk assessment of novel coronavirus (COVID-19) cases: A data-driven analysis // Chaos, Solitons & Fractals, 2020, vol.135, 109850. DOI: 10.1016/j.chaos.2020.109850.
  • Tyrrell D. A., and Bynoe M. L. Cultivation of viruses from a high proportion of patients with colds // Lancet, 1966, vol. 1 (7428), pp.76–77.
  • Velavan T.P., and Meyer C.G. The COVID-19 epidemic // Tropical medicine & international health, 2020, vol.25(3), pp.278–280.
  • Rustam F., Reshi A. A., Mehmood A., Ullah S., On B., Aslam W., and Choi G. S. COVID-19 future forecasting using supervised machine learning models // IEEE Access, 2020, vol.8, pp.101489–101499. DOI: 10.1109/ACCESS.2020.2997311.
  • Petropoulos F., and Makridakis S. Forecasting the novel coronavirus COVID-19 // PloS one, 2020, 15(3), e0231236. DOI: 10.1371/journal.pone.0231236.
  • Roosa K., Lee Y., Luo R., Kirpich A., Rothenberg R., Hyman J.M., and Chowell G. Short-term forecasts of the COVID-19 epidemic in Guangdong and Zhejiang, China: February 13–23, 2020 // Journal of Clinical Medicine, 2020, 9(2), 596. DOI: 10.3390/jcm9020596.
  • Hu Z., Ge Q., Jin L., and Xiong M. Artificial intelligence forecasting of COVID-19 in China. arXiv preprint arXiv:2002.07112, 2020, 20 p.
  • Liu D., Clemente L., Poirier C., Ding X., Chinazzi M., Davis J. T., Vespignani A., and Santillana M. A machine learning methodology for real-time forecasting of the 2019-2020 COVID-19 outbreak using Internet searches, news alerts, and estimates from mechanistic models. arXiv preprint arXiv:2004.04019, 2020, 23 p.
  • Chimmula V.K.R., and Zhang L. Time series forecasting of COVID-19 transmission in Canada using LSTM networks // Chaos, Solitons & Fractals, 2020, vol.135, 109864. DOI: 10.1016/j.chaos.2020.109864.
  • Azarafza M., Azarafza M., and Tanha J. COVID-19 Infection Forecasting based on deep learning in Iran. medRxiv. 2020, 7 p.
  • Punn N. S., Sonbhadra S. K., and Agarwal S. COVID-19 epidemic analysis using Machine Learning and DeepLearning algorithms. medRxiv. 2020, 10 p.
  • Bandyopadhyay S. K., and Dutta S. Machine learning approach for confirmation of COVID-19 cases: Positive, negative, death and release. medRxiv, 2020, 10 p.
  • Pathan R.K., Biswas M., and Khandaker M.U. Time series prediction of COVID-19 by mutation rate analysis using recurrent neural network-based LSTM model // Chaos, Solitons & Fractals, 2020, vol. 138, 110018. DOI: 10.1016/j.chaos.2020.110018.
  • Benvenuto D., Giovanetti M., Vassallo L., Angeletti S., and Ciccozzi M. Application of the ARIMA model on the COVID-2019 epidemic dataset // Data in brief, 2020, vol.29, 105340. DOI: 10.1016/j.dib.2020.105340.
  • Perone G. An ARIMA model to forecast the spread and the final size of COVID-2019 epidemic in Italy. medRxiv. 2020, 14 p.
  • Vandeput N. Forecast KPI: RMSE, MAE, MAPE and Bias. Data Science for Supply Chain Forecast, 2019, 237 p.
  • Medium, https://medium.com/@kangeugine/time-series-arima-model-11140bc08c6
  • Liu Q., Liu X., Jiang B., and Yang W. Forecasting incidence of hemorrhagic fever with renal syndrome in China using ARIMA model // BMC Infectious Diseases, 2011, vol.11 (1), 7 p. DOI: 10.1186/1471-2334-11-218.
  • GitHub, https://github.com/owid/covid-19-data/tree/master/public/data
  • Kaggle, https://www.kaggle.com/datasets
  • Shahid F., Zameer A., and Muneeb M. Predictions for COVID-19 with deep learning models of LSTM, GRU and Bi-LSTM // Chaos, Solitons & Fractals, 2019, vol. 140, Article 110212. DOI: 10.1016/j.chaos.2020.110212.
  • Wikipedia, https://en.wikipedia.org/wiki/Akaike_information_criterion