| Abstrakt: |
Time series forecasting remains a challenging task owing to its nonlinear, complex, and chaotic behaviour. The purpose of the current paper was to analyze the forecast performance of different models to determine Pakistan's macroeconomic variables, such as inflation, exchange rate, and stock return. These models included Linear Autoregressive Integrated Moving Average (ARIMA) model as well as nonlinear models, such as Artificial Neural Networks (ANN), and Support Vector Machine (SVM). Afterwards, a hybrid methodology was used to combine the linear ARIMA with nonlinear models of ANN and SVM. The forecasting performance of all the models, that is, ARIMA, ANN, SVM, ARIMA-ANN, and ARIMASVM was compared on the basis of RMSE and MAE. The results indicated that the best forecasting model to achieve high forecast accuracy was the hybrid ARIMA-SVM. [ABSTRACT FROM AUTHOR] |
