Analisis Penggunaan Orange Data Mining untuk Prediksi Harga USDT/BIDR Binance

Abstract

The results of implementing Orange Data Mining for predicting USDT/BIDR prices are displayed in the Test and Score widget. In the conducted test, RMSE and MAE values were obtained for each model. The K-Nearest Neighbor (K-NN) method had RMSE and MAE values of 0.002 and 0.002, while the Support Vector Machine (SVM) method had RMSE and MAE values of 0.0003 and 0.002. The Linear Regression method had RMSE and MAE values of 0.0000 and 0.000. Based on these RMSE and MAE values, it can be concluded that the Linear Regression method is the best method for predicting changes in USDT/BIDR prices compared to the K-Nearest Neighbor and SVM methods. Further research is needed to investigate this best method for future studies. It is recommended that future research compares the Linear Regression method with other methods using Orange tools or implements other relevant tools.