A Model Selection Approach for Time Series Forecasting: Incorporating Google Trends Data in Australian Macro Indicators
Entropy · 30.07.2023 · 25 (8) · 1144
DOI: 10.3390/e25081144 ↗Kurz gefasst
Fachartikel in der Zeitschrift Entropy, online erschienen am 30.07.2023. Verfasst von Ali Abdul Karim und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science and Information Technology, La Trobe University, Melbourne, VIC 3086, Australia. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
This study examined whether the behaviour of Internet search users obtained from Google Trends contributes to the forecasting of two Australian macroeconomic indicators: monthly unemployment rate and monthly number of short-term visitors. We assessed the performance of traditional time series linear regression (SARIMA) against a widely used machine learning technique (support vector regression) and a deep learning technique (convolutional neural network) in forecasting both indicators across different data settings. Our study focused on the out-of-sample forecasting performance of the SARIMA, SVR, and CNN models and forecasting the two Australian indicators. We adopted a multi-step approach to compare the performance of the models built over different forecasting horizons and assessed the impact of incorporating Google Trends data in the modelling process. Our approach supports a data-driven framework, which reduces the number of features prior to selecting the best-performing model. The experiments showed that incorporating Internet search data in the forecasting models improved the forecasting accuracy and that the results were dependent on the forecasting horizon, as well as the technique. To the best of our knowledge, this study is the first to assess the usefulness of Google search data in the context of these two economic variables. An extensive comparison of the performance of traditional and machine learning techniques on different data settings was conducted to enable the selection of an efficient model, including the forecasting technique, horizon, and modelling features.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Computer Science and Information Technology, La Trobe University, Melbourne, VIC 3086, Australia.
ORCID-Profile: Ali Abdul Karim, Eric Pardede
Zitieren
APA
Karim, A. A., Pardede, E., & Mann, S. (2023). A Model Selection Approach for Time Series Forecasting: Incorporating Google Trends Data in Australian Macro Indicators. Entropy, 25(8), 1144. https://doi.org/10.3390/e25081144
Vancouver
Karim AA, Pardede E, Mann S. A Model Selection Approach for Time Series Forecasting: Incorporating Google Trends Data in Australian Macro Indicators. Entropy. 2023;25(8):1144. doi:10.3390/e25081144
BibTeX
@article{Karim2023,
author = {Karim, Ali Abdul and Pardede, Eric and Mann, Scott},
title = {A Model Selection Approach for Time Series Forecasting: Incorporating Google Trends Data in Australian Macro Indicators},
journal = {Entropy},
year = {2023},
volume = {25},
number = {8},
pages = {1144},
doi = {10.3390/e25081144}
}
EUVIMED