Analisis Kinerja Algoritma Prediksi Saham pada PT GoTo Gojek Tokopedia Tbk (GOTO)

The growth of stock investment in Indonesia is not merely a domestic phenomenon but also has global implications. Indonesia's capital market, with active participation from domestic players and foreign investors, significantly contributes to economic performance. This research aims to identify the best method for predicting the stock prices of PT GoTo Gojek Tokopedia Tbk (GOTO) through a comparison of K-Nearest Neighbors (KNN), Support Vector Machine (SVM), and Linear Regression. The study utilizes Google Colab as an evaluation platform with stock price data covering market variations. Three methods are evaluated based on Root Mean Squared Error (RMSE) and Mean Absolute Error (MAE) values. Performance evaluation reveals that Linear Regression exhibits near-zero MSE (9.82e-27), RMSE of 9.91e-14, and MAE of 8.71e-14, indicating exceptionally high prediction accuracy compared to KNN and SVM. Based on the evaluation results, Linear Regression stands out as the optimal choice for predicting GOTO stock prices. This finding provides guidance for investors and analysts in making investment decisions.