Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal KOMPUTIKA - Jurnal Sistem Komputer
Silalahi, Rosalia Natal
Unknown Affiliation
Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Perbandingan Kinerja Metode Linear Regression, LSTM dan GRU Untuk Prediksi Harga Penutupan Saham Coco-Cola Silalahi, Rosalia Natal; Muljono, Muljono
Komputika : Jurnal Sistem Komputer Vol. 13 No. 2 (2024): Komputika: Jurnal Sistem Komputer
Publisher : Computer Engineering Departement, Universitas Komputer Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34010/komputika.v13i2.12265

Abstract

In the stock market, making predictions about stock price movements is crucial for traders, as this will affect their potential profits or losses. The accuracy of the prediction results largely depends on the method used and the quality of the data available. Therefore, this research chooses the subject of predicting the stock price of Coco-Cola. This research will conduct a comparison between several different time series data analysis methods. These methods include Linear Regression, LSTM, and GRU. The comparison of the three methods with window-width variations of 3, 4, and 5 provides an in-depth insight into the performance of each model. The comparison results show that the model achieves the best performance when using window-width=3 in the Linear Regression method. Linear Regression with MSE of 0.24, RMSE of 0.49, shows better performance compared to LSTM (2.72 & 1.65) and GRU (0.31 & 0.55). This research provides valuable guidance for future predictive model development, with a focus on improving the accuracy and precision of stock price predictions.
Co-Authors Muljono Muljono