Prediction Modelling of COVID-19 Outbreak in Indonesia using a Logistic Regression Model

Abstract

The COVID-19 outbreak has changed the world at large since it was announced by the World Health Organization (WHO). Many policies in various countries were then implemented to control its spread. Most aspects of human life and the environment are affected by this pandemic. This paper aims to determine the prediction model for the COVID-19 outbreak in Indonesia. The approach used for this modelling employs a logistic regression model. The data modeled in this paper is data on the distribution of COVID-19 sufferers and data on patients who have recovered from COVID-19 in Indonesia. The data obtained as research material were taken from March 2, 2020, to November 12, 2020. From the results of this paper, this prediction model obtained logistic regression coefficient values for data on COVID-19 sufferers in Indonesia of 8.114748 and 0.750743, while the coefficient values for data on sufferers who recovered from COVID-19 were 9.360925 and 0.788334. The results of the prediction model for sufferers and people who have recovered from COVID-19 have the same accuracy value, namely mean absolute error (MAE) of 0.02, mean square error (MSE) of 0.00, and R2 of 0.99.