The concept of foreign trade, which has a history of about two and a half centuries and is of great importance for foreign economies, plays a key role in the development and development of national economies in today's global competitive environment. Export has an important place in foreign trade transactions. Because there is a driving force between exports, economic growth, foreign exchange and capital input. The aim of the study carried out using artificial neural networks to estimate the value of Turkey's exports and thus contribute to the literature is presented. In order to estimate the export dependent variable, gross capital formation, industry, savings, exchange rate, logistics, gross domestic product, per capita gross domestic product, commercial service export and commodity export were selected. A model with artificial neural networks has been established and analyzed by using MATLAB R2013a program with 256 data in total covering sixteen years between 2002-2017. As a result of the experiments with 2-9 hidden layers, the best result was found to be when the number of hidden layers was 9. When the number of hidden layers is 9, R2 = 0.99, RMSE = 3611616, MAE = 2613313 and MAPE = 45.14141. The findings by producing strong statistical results to estimate the value of Turkey's exports of artificial neural networks has shown that successful.
Benzer Makaleler | Yazar | # |
---|
Makale | Yazar | # |
---|