Article Per Year (5 Year)
p-Index From 2021 - 2026
0.817
P-Index
This Author published in this journals
All Journal Jurnal Ilmiah SIGMA: Informatics Engineering Journal of UPB SAINTEK TECHNOMEDIA : Informatics and Computer Science
Arif Susilo
Unknown Affiliation
Automotive Engineering Civil Engineering, Building, Construction & Architecture Computer Science & IT Decision Sciences, Operations Research & Management Engineering Industrial & Manufacturing Engineering

Published : 4 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search
Journal : TECHNOMEDIA : Informatics and Computer Science

 1 
Pemodelan Prediksi Harga Saham Emas ANTAM Menggunakan Gated Recurrent Unit dan Regresi Linear Berganda pada Time Series Kamalia, Antika Zahrotul; Wahyu Tri Utami; Arif Susilo
Tekompedia : Jurnal Ilmiah Ilmu Komputer Vol 3 No 1 (2026): Januari
Publisher : CV Nature Creative Innovation

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58641/technomedia.v3i1.185

Abstract

This study investigates the prediction of PT Aneka Tambang Tbk (ANTM) stock prices using time-series data by comparing two approaches: the Gated Recurrent Unit (GRU) model and multiple linear regression. The dataset consists of daily historical ANTM data collected from Yahoo Finance spanning 2014–2024, which was preprocessed (including cleaning/normalization) and split chronologically into training (70%) and testing (30%) sets to preserve realistic forecasting conditions. Model performance was assessed using R-squared (R²), Mean Absolute Error (MAE), Mean Squared Error (MSE), and Root Mean Squared Error (RMSE), supported by visual comparisons between actual and predicted values. The results indicate that the GRU model achieves superior predictive performance and better captures the dynamic and non-linear behavior of stock price movements compared to multiple linear regression. These findings suggest that GRU is more suitable for ANTM stock price forecasting in a time-series setting, while multiple linear regression remains useful as a simple and interpretable baseline model.
Co-Authors Antika Zahrotul Kamalia Nurjanah Rahman Ali Wahyu Tri Utami Yoga Purnomo