 Forecasting Turkey’s Exports and Imports via Artificial Neural NetworkAslı Seda Kurt Fiscaoeconomia, 2022, issue 2 Abstract: Foreign trade has been one of the prominent areas of interest since the emergence of nation states. The aim of this study is to forecast exports and imports for the Turkish economy using artificial neural networks. Machine learning and artificial neural networks are relatively new methods in the economics literature, and in recent years, there has been an increase in evaluations that the predictions made by these methods are more effective. The findings of the study, in which the data gathered from Turkish Statistical Institute for the period of 1923-2019 (yearly) and from The Central Bank of The Republic of Turkey for the period of 1992:1-2021:6 (monthly), support this view. The pandemic process has once again revealed that economic variables can also be affected dramatically by non-economic reasons. For all these reasons, it is obvious how important it is to be able to forecast foreign trade series, although it is difficult. This is the main motivation of this study. It has been observed that artificial neural networks allow successful forecast results in the process when all macroeconomic indicators were affected dramatically due to the pandemic. The results of this and similar studies will be a guide for all policy practitioners and economic agents. Keywords: Exports; Imports; Artificial Neural Network (search for similar items in EconPapers) Downloads: (external link) Related works: Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text Persistent link: https://EconPapers.repec.org/RePEc:fis:journl:220223 Access Statistics for this article More articles in Fiscaoeconomia from Tubitak Ulakbim JournalPark (Dergipark) |
Is your work missing from RePEc? Here is how to contribute.
Questions or problems? Check the EconPapers FAQ or send mail to .
EconPapers is hosted by the
School of Business at Örebro University.