Model Average-Based Fuzzy Time Series untuk Prediksi Perkembangan Kasus Terkonfirmasi Positif COVID-19

Abstract

The number of positive confirmed COVID-19 cases in Indonesia continues to rise on a daily basis. A prediction model is required to examine and measure the current progression of positive verified COVID-19 instances and to anticipate these circumstances in the future. The goal of this research is to create a prediction application that uses a fuzzy time series approach as a prediction method and an average-based length algorithm as an interval length determinant. The effective interval length can have a greater impact on the prediction outcomes. The data for this study came from the COVID-19 task force's website, and it tracked the progression of positive confirmed COVID-19 cases from November 2020 to July 2021. The Mean Absolute Percentage Error (MAPE) is relatively little based on the findings of the prediction application performance. This can help the management unit make decisions by giving information and establishing policies relating to actual efforts to prepare for, plan for, prevent, and control the spread of COVID-19.

Keywords

• average-based, covid-19, forecasting, fuzzy time series, prediction