Forecasting Stock Price Index of Four Asian Countries During COVID-19 Pandemic Using ARMA-GARCH and RNN Methods

The COVID-19 pandemic has had a significant impact on the global economy, including the stock markets of many Asian countries. Forecasting stock prices is a challenging task, but it is essential for investors to make informed decisions. This study compares the performance of ARMA-GARCH and RNN models in forecasting the stock price index of four Asian countries (China, Indonesia, Japan, and South Korea) during the COVID-19 pandemic. The results show that the RNN model outperforms the ARMA-GARCH model in terms of forecasting accuracy, as measured by R-squared. The findings of this study suggest that RNN models are a more promising approach for forecasting stock prices during times of economic uncertainty. However, the methods used in this research can be further developed to improve model accuracy and precision. For example, future research could explore the use of longer time periods, other RNN variants such as LSTM, different data splitting techniques, and other hyperparameter tuning strategies.