Enhancement Support Vector Regression Using Black Widow Optimization for Predicting Foreign Exchange Rate

Abstract

Prediction of foreign exchange rates is one of the time series problems that have fluctuating value movements. There are several algorithms that can make predictive models for this problem, one of which is Support Vector Regression (SVR). In this study, foreign exchange rate predictions were made using Hybrid SVR and Black Widow Optimization (BWO). This is done with the aim of improving the performance of the SVR in order to produce a better predictive model for the EUR/USD foreign exchange rate data in 2020. The results of the proposed algorithm get better performance in terms of R2, MSE, RMSE, MAE, and MAPE compared to SVR.