Application of generalised regression neural network for financial time series forecasting: a comprehensive comparison with autoregressive integrated moving average
Time series forecasting plays a crucial role in fields such as economics, business, and finance. Traditional models like the autoregressive integrated moving average (ARIMA) have been widely used for their accuracy. However, advances in computing and the rise of machine learning (ML) and deep learning (DL) have introduced powerful alternatives. This study examines the performance of a DL-based method - the generalised regression neural network (GRNN) - compared to ARIMA. Results show that GRNN significantly outperforms ARIMA in forecasting accuracy, with an error margin of less than 5%. GRNN also achieves better results across statistical metrics, including mean absolute error (MAE), root mean square error (RMSE), and mean absolute percentage error (MAPE). Additionally, GRNN offers faster training times, making it especially advantageous in scenarios requiring rapid and frequent forecasts. These findings highlight GRNN's potential as a superior tool for time series prediction in dynamic, data-driven environments.