A Comparative Study of Autoregressive and Neural Network Models: Forecasting the GARCH Process

Document Type

Book Chapter

Source of Publication

Lecture Notes in Computer Science

Publication Date

8-16-2022

Abstract

The Covid-19 pandemic has highlighted the importance of forecasting in managing public health. The two of the most commonly used approaches for time series forecasting methods are autoregressive (AR) and deep learning models (DL). While there exist a number of studies comparing the performance of AR and DL models in specific domains, there is no work that analyzes the two approaches in the general context of theoretically simulated time series. To fill the gap in the literature, we conduct an empirical study using different configurations of generalized autoregressive conditionally heteroskedastic (GARCH) time series. The results show that DL models can achieve a significant degree of accuracy in fitting and forecasting AR-GARCH time series. In particular, DL models outperform the AR-based models over a range of parameter values. However, the results are not consistent and depend on a number of factors including the DL architecture, AR-GARCH configuration, and parameter values. The study demonstrates that DL models can be an effective alternative to AR-based models in time series forecasting.

ISSN

0302-9743

Publisher

Springer International Publishing

Volume

13395

First Page

589

Last Page

603

Disciplines

Computer Sciences

Keywords

Time series forecasting, Neural networks, Deep learning, ARIMA, GARCH

Scopus ID

85137267629

Indexed in Scopus

yes

Open Access

no

Link to Full Text

Share

COinS