Prediksi Harga Ekspor Non Migas di Indonesia Berdasarkan Metode Estimator Deret Fourier dan Support Vector Regression

Abstract

Economic growth is one of the indicators in the Sustainable Development Goals (SDGs) on increasing economic activity. One of the activities that supports the running of the economy is trade between countries, such as exports. In Indonesia, non-oil and gas exports have played an important role in total exports in recent years, including coal exports being the main export. Therefore, price predictions for Indonesia's non-oil and gas exports are very important as material for evaluating policies to encourage economic growth. This is the main focus of this research. In this study, non-oil and gas export price forecasts are made taking into account current issues such as the COVID-19 pandemic and the Russia-Ukraine war. The accuracy of the model obtained from the Fourier series estimator and Support Vector Regression (SVR) is investigated by comparing the Mean Absolute Percentage Error (MAPE) value to predict Indonesia's non-oil and gas export prices. The results of the study show that the COVID-19 pandemic and the Russia-Ukraine war have had a significant impact on non-oil and gas export prices. The SVR model with the Radial Basis Function (RBF) kernel shows better accuracy than the Fourier series estimator model of the cos sin function, with MAPE values of 9.29 and 15.26% for each test data, respectively. Therefore, this study is expected to be the basis for formulating policies related to regulating non-oil and gas export processes to support economic growth in Indonesia.