Amerikan doları kurunun yapay sinir ağları yöntemiyle tahminlenmesi: 2009 – 2021 dönemi
Estimating the American Dollar Exchange Rate by Artificial Neural Networks: 2009 – 2021 Period

Summary/Abstract: In this study, it is aimed to estimate the exchange rate of US Dollar in Turkish Lira (referred to as dollar in the rest of the study) by artificial neural network method and to determine whether the artificial neural network method is successful in estimating the dollar exchange rate. For this purpose, the artificial neural network was trained with the data of seven different time series in the period 2009 - 2021 and the same period was estimated. Estimated values were compared with actual values and error metrics were calculated. All data used in the study were obtained from the Central Bank of the Republic of Turkey Electronic Data Delivery System. The data were analyzed using the MATLAB 2013 program. After the analysis, MAE, MSE and MAPE error metrics were calculated. According to the results obtained, the MAE value was calculated as 0,01738, the MSE value as 0,0019355, and the MAPE value as 0,5137. This finding shows that the established model estimates the dollar exchange rate with an error rate of 0,5137% (approximately five per thousand).

• Details
• Contents