Forecasting Turkish Lira (TRY)/US Dollar (USD) Interest Exchange Rates Using Machine Learning Methodologies

Authors : Mahmut DİRİK

Pages : 120-131

View : 17 | Download : 7

Publication Date : 2021-12-15

Article Type : Research Paper

Abstract :Machine learning algorithms have become increasingly popular in recent years for analyzing financial data and predicting the exchange rate system. The aim of this paper was to construct an investment appreciation rate estimation model based on machine learning by estimating the Turkish lira/US dollar exchange rate. The forecasting model was developed using foreign exchange market data, namely the exchange rates in TL and USD at specific periods. The proposed model was estimated using machine learning methods such as Multilayer Perceptron insert ignore into journalissuearticles values(MLP);, Linear Regression insert ignore into journalissuearticles values(LR);, Support Vector Machine insert ignore into journalissuearticles values(SVM);, Random Forest insert ignore into journalissuearticles values(RF);, and Local Weighted Learning insert ignore into journalissuearticles values(LWL);. The model`s validity was established using TRY interest rates and the USD exchange rate. The data were analyzed using mean absolute error insert ignore into journalissuearticles values(MAE);, directional accuracy insert ignore into journalissuearticles values(DA);, mean square error insert ignore into journalissuearticles values(MSE);, and root mean square error insert ignore into journalissuearticles values(RMSE);. These metric results show that the proposed model is suitable for both prediction and investment data.
Keywords : Machine Learning, Exchange Rate Prediction, Regression, MLP, SVM, RF, LWL