PREDICTION OF GOLD PRICES USING HYBRID MODEL ARIMA-LSTM
Advances and Applications in Statistics · 2025
DOI: 10.17654/0972361725031 ↗Kurz gefasst
Fachartikel in der Zeitschrift Advances and Applications in Statistics, 2025. Verfasst von Woon Kah Mun und 3 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref).
Abstract (Originalsprache)
Time series forecasting has been gaining attention since the COVID-19 pandemic to predict sales, economics, and weather outcomes. In this research, an empirical study on a time series model was done to predict daily gold prices using historical everyday gold prices from 1st January 2020 to 31st December 2021 as the training and testing dataset. The performance of autoregressive integrated moving average (ARIMA), long short-term memory (LSTM) and hybrid-model ARIMA-LSTM was compared through their mean absolute percentage error (MAPE) and root mean-squared error (RMSE) values. The results showed that the model with the smallest RMSE was the hybrid ARIMA-LSTM, but the model with the smallest MAPE was LSTM.
Zitieren
APA
Mun, W. K., Sufahani, S. F., Kamil, A. A., & Nawawi, M. K. M. (2025). PREDICTION OF GOLD PRICES USING HYBRID MODEL ARIMA-LSTM. Advances and Applications in Statistics. https://doi.org/10.17654/0972361725031
Vancouver
Mun WK, Sufahani SF, Kamil AA, Nawawi MKM. PREDICTION OF GOLD PRICES USING HYBRID MODEL ARIMA-LSTM. Advances and Applications in Statistics. 2025. doi:10.17654/0972361725031
BibTeX
@article{Mun2025,
author = {Mun, Woon Kah and Sufahani, Suliadi Firaus and Kamil, Anton Abdulbasah and Nawawi, Mohd Kamal Mohd},
title = {PREDICTION OF GOLD PRICES USING HYBRID MODEL ARIMA-LSTM},
journal = {Advances and Applications in Statistics},
year = {2025},
doi = {10.17654/0972361725031}
}
EUVIMED