NORMA eResearch @NCI Library

Worldwide differences of Covid-19 on cases and deaths using time series forecasting models

Chandani, Ankish Kumar (2020) Worldwide differences of Covid-19 on cases and deaths using time series forecasting models. Masters thesis, Dublin, National College of Ireland.

[img]
Preview
PDF (Master of Science)
Download (2MB) | Preview
[img]
Preview
PDF (Configuration manual)
Download (1MB) | Preview

Abstract

Millions of people have been infected and hundreds of thousands have died due to a deadly disease Covid-19. Hence, it has become a significant research area since it started spreading around the world. Covid-19 forecasting demands accurate reported count to analyze time-related data along with complex model implementation. Accurate Covid-19 forecasting is critical for planned action to combat this disease and take necessary precautionary measures to reduce its impact. The United States has been ranked as the most impacted country in the world and Italy have the lowest mortality rate among the countries infected with more than 150,000. Implementation of advanced forecast models can help in acquiring valuable future forecasting which could aid governments as well as health organizations to work together and guide the public to help prevent this virus. A novel forecast model, Prophet1 has been implemented in this research to predict and forecast future Covid-19 cases and deaths precisely. Comparison of model error and forecast data was performed for the machine learning methods i.e. Polynomial Regression, Holt’s Linear Model, and time series such as AR, ARIMA model. Evaluation metrics such as MAPE, RMSE and MAE have been used to evaluate the model performance. Research finding signifies the most efficient model to be ARIMA and Prophet. ARIMA and Prophet model gave a better performance in predicting and forecasting the total Covid-19 cases and deaths respectively along with the lowest combined evaluation errors. This approach can assist the governments to put necessary regulations in place before millions more get infected and also prevent the loss of billions worth of money.
Index Terms: Covid-19, Prediction, Forecasting, Time Series, ARIMA, Prophet

Item Type: Thesis (Masters)
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science

Q Science > QA Mathematics > Computer software
T Technology > T Technology (General) > Information Technology > Computer software

R Medicine > RA Public aspects of medicine
Divisions: School of Computing > Master of Science in Data Analytics
Depositing User: Dan English
Date Deposited: 22 Jan 2021 11:03
Last Modified: 22 Jan 2021 11:03
URI: http://norma.ncirl.ie/id/eprint/4434

Actions (login required)

View Item View Item