Pantauan Prediktif Covid-19 Dengan Menggunakan Metode SIR dan Model Statistik Di Indonesia

Abstract

During the COVID-19 pandemic, many attempts have been made to predict cases of additional patients, deaths and other medical indicators using various methods. Several forecast projects and predictions have influenced policies in several countries, including Indonesia. However, predictions and predictions for the COVID-19 pandemic are inherently uncertain. Uncertainty is rooted in a lot of the unknown. Starting from the virus itself, complexity, heterogeneity, human behavior, protocols and government intervention. In this study we explored the potential using the term "Predictive Monitoring" using the SIR method and statistical models. This method was chosen because it is one of the basic methods in epidemiological models. The purpose of this research is to capture and understand changes that occur as meaningful signals of uncertainty over changes in actual scenarios. The results of predictive monitoring obtained from this study amounted to 0.89 or 89% for the cure rate and 0.64 or 64% for the mortality rate. With this signal, it is hoped that the planning, behavior and mentality of the current community will become more forward-looking in initiating and guiding preventive actions to shape the real future. Keywords—Data Science, Forecasting, Model SIR, COVID-19