Artificial Neural Networks in Export and Import Forecasting: An Analysis of Opportunities
Mykhailo Luchko, Nataliia Dziubanovska, Oksana Arzamasova · 2021 11th IEEE International Conference on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications (IDAACS) · 2021
The paper concerns the issue of forecasting trends in trade relations between Malaysia and Ukraine using artificial neural networks. The current state of trade relations between the countries in the context of the COVID-19 pandemic has been analyzed. Considering the advantages and disadvantages of the types of neural networks built into the software product STATISTICA 10, MLP network has been chosen to build a predictive model of imports and exports of goods. The forecast values for the volumes of exports and imports of goods for the period from January 2021 to December 2022 have been calculated. Comparing the results, the researchers concluded that the artificial neural network is the most successful model for forecasting imports and exports. Suggestions for effective evaluation and forecasting of international trade indicators using the theory of time series and neural network technologies are given and the directions of further scientific research arising from this paper are formed.