Comparative Analysis of Machine Learning and Traditional Methods in Turkey's Gross Domestic Product Forecasting

Hakan Kaya () and Batuhan Özkan ()
Additional contact information
Hakan Kaya: Faculty of Economics and Administrative Sciences, Economics Department, Bitlis Eren University, Bitlis, Turkey;
Batuhan Özkan: Faculty of Science and Literature, Department of Statistics, Bitlis, Turkey;

Journal for Economic Forecasting, 2025, issue 3, 110-127

Abstract: In this study, the Gross Domestic Product (GDP) is forecasted using data from a sample of Turkey covering the period between 1991 and 2020. The aim of the study is to compare the forecasting performance of traditional econometric models and machine learning (ML) methods. In this way, in cases where the assumptions and limitations of traditional methods cannot be met, the potential of ML methods with fewer assumptions and constraints is evaluated as an alternative approach to be preferred by researchers. Among the traditional methods, ARIMA (AutoRegressive Integrated Moving Average) model is used in the study, while Artificial Neural Networks (ANN), Elastic Net, Support Vector Machine (SVM) and Extreme Gradient Boosting (XGBoost) models are used as ML methods. Error metrics such as R-squared, MSE (Mean Squared Error), RMSE (Root Mean Squared Error), MAE (Mean Absolute Error) and Scatter Index were used to compare the prediction performance of the models. The results show that XGBoost performs the best with high prediction accuracy (R-square = 0.99999) and low error rates (RMSE = 0.00134, MAE=0.00071). In addition, the forecasting performance of other ML models is better than that of the traditional ARIMA model. This study shows that ML methods are more effective and flexible than traditional methods in forecasting macroeconomic indicators such as GDP.

Keywords: Gross Domestic Product; Artificial Neural Networks; Elastic Net; Support Vector Machine; XGBoost (search for similar items in EconPapers)
JEL-codes: C22 C45 C53 (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.ipe.ro/ftp/RePEc/rjef3_2025/rjef3_2025p110-127.pdf

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:rjr:romjef:v::y:2025:i:3:p:110-127

Access Statistics for this article

Journal for Economic Forecasting is currently edited by Lucian Liviu Albu and Corina Saman

More articles in Journal for Economic Forecasting from Institute for Economic Forecasting Contact information at EDIRC.
Bibliographic data for series maintained by Corina Saman ( this e-mail address is bad, please contact ).