Citation

Prabakaran, Nyaanaputhraan and Palanichamy, Naveen and Kumaresan, Prabha (2026) Comparative Study on Gold Price Prediction Using Machine Learning. JOIV : International Journal on Informatics Visualization, 10 (2). p. 696. ISSN 2549-9610

Text 3542-14823-1-PB.pdf - Published Version Restricted to Repository staff only Download (3MB)

Abstract

Gold is consistently known as an item of value and has formally used to be the backbone of world currency. Financial analysts and professionals have analyzed gold prices as an indicator of global market conditions, and, due to its volatility, it is considered a high yielding investment. Recently, many analysts and institutional traders have shifted from traditional methods such as technical and fundamental analysis to machine learning (ML) for prediction. Past research on gold price prediction has focused on using historical price data and traditional economic indicators, while the United States (US) unemployment rate is often overlooked. Our primary objective is to investigate the potential of ML and deep learning (DL) models in predicting gold prices by incorporating the unemployment rate. In this study, the ML models included support vector regression (SVR) and random forest (RF), with DL models such as the long short-term memory (LSTM) and gated recurrent units (GRU). Measurements were performed using Root Mean Squared Error (RMSE) and Mean Absolute Error (MAE), which showed that GRU yielded more accurate predictions, with RMSE of 0.046417 and MAE of 0.033409, compared to LSTM. The performance value of the SVR model was best when only one lag was used, while five lags were used for the RF model. The autoregressive integrated moving average (ARIMA) model achieved competitive performance, with RMSE 0.214355 and MAE 0.169709, indicating the effectiveness of traditional ML techniques combined with advanced DL methodologies for predicting gold prices.

Item Type:	Article
Uncontrolled Keywords:	Gold price, prediction, macroeconomic data, machine learning, deep learning
Subjects:	Q Science > QA Mathematics > QA71-90 Instruments and machines
Divisions:	Faculty of Computing and Informatics (FCI)
Depositing User:	Ms Suzilawati Abu Samah
Date Deposited:	05 Jun 2026 00:39
Last Modified:	05 Jun 2026 00:39
URII:	http://shdl.mmu.edu.my/id/eprint/15955

Downloads

Edit (login required)