Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal Journal of Information Technology and Computer Science
Aditama, Gustian
Unknown Affiliation
Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering Engineering

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

Found 1 Documents
Search

 1 
Gold Prices Prediction using Univariate Long Short Term Memory Method Aditama, Gustian; Yudistira, Novanto; Mahmudy, Wayan Firdaus
Journal of Information Technology and Computer Science Vol. 10 No. 2: August 2025
Publisher : Faculty of Computer Science (FILKOM) Brawijaya University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25126/jitecs.2025102525

Abstract

Gold is one of the precious metals that serves various purposes beyond being a jewelry material. When it comes to gold, it is often associated with the economy. Before the existence of currency, humans used gold as the base material for coins as a medium of exchange. Currently, one of the commonly utilized functions of gold is as an investment asset. Due to its utility and high demand, the price of gold can fluctuate over time. This research aims to predict the price of gold using the Long Short Term Memory (LSTM) method. LSTM is a deep learning technique that performs well when applied to time series data. The performance of LSTM can be assessed using metrics such as Mean Absolute Percentage Error (MAPE) and Root Mean Squared Error (RMSE). Thus, this study proposes the prediction of gold prices using LSTM with an optimized architecture. In order to achieve it, testing is conducted based on sequence length and hidden size. The best results were achieved using Univariate LSTM with a sequence length of 25 and a hidden size of 150, that produce RMSE of 22.014 and MAPE of 1.133%.
Co-Authors Novanto Yudistira Wayan Firdaus Mahmudy