Short-Term Forecasting COVID-19 Cases In Turkey Using Long Short-Term Memory Network

TL;DR

This study evaluates LSTM networks for short-term COVID-19 case forecasting in Turkey, comparing its accuracy with traditional methods and finding that adding death data improves predictions, though Holt-Winters performs better overall.

Contribution

It demonstrates the effectiveness of LSTM networks in COVID-19 case forecasting and shows that incorporating death data enhances prediction accuracy.

Findings

LSTM achieves a mean absolute error of 1.69% for 15-day forecasts.

Adding death data reduces LSTM error to 0.99%.

Holt-Winters method outperforms LSTM in accuracy.

Abstract

COVID-19 has been one of the most severe diseases, causing a harsh pandemic all over the world, since December 2019. The aim of this study is to evaluate the value of Long Short-Term Memory (LSTM) Networks in forecasting the total number of COVID-19 cases in Turkey. The COVID-19 data for 30 days, between March 24 and April 23, 2020, are used to estimate the next fifteen days. The mean absolute error of the LSTM Network for 15 days estimation is 1,69$\pm$1.35%. Whereas, for the same data, the error of the Box-Jenkins method is 3.24$\pm$1.56%, Prophet method is 6.88$\pm$4.96% and Holt-Winters Additive method with Damped Trend is 0.47$\pm$0.28%. Additionally, when the number of deaths data is also provided with the number of total cases to the input of LSTM Network, the mean error reduces to 0.99$\pm$0.51%. Consequently, addition of the number of deaths data to the input, results a lower error in forecasting, compared to using only the number of total cases as the input. However, Holt-Winters Additive method with Damped Trend gives superior results to LSTM Networks in forecasting the total number of COVID-19 cases.