Hybrid Model Approaches for Accurate Time Series Predicting of COVID-19 Cases

Abstract

This study compares the performance of ARIMA, LSTM, and hybrid models in predicting COVID-19 cases and analyzing forecast errors. Utilizing real-world data, the models were assessed for accuracy and trend prediction over numerous months. Heatmaps of prediction errors revealed that the hybrid model reliably outperformed ARIMA and LSTM by accomplishing lower error extents. The findings highlight the preferences of combining statistical and deep learning approaches for time series predicting. The results contribute to progressing predicting accuracy, which is basic for pandemic response arranging and public health administration.