Kurniasari, Dian and Kenny, Stevanus and Warsono, Warsono and Widiarti, Widiarti (2025) Forecasting Silver Prices Using the Long Short-Term Memory (LSTM) Method. International Journal of Advanced Multidisciplinary Research and Studies, 5 (2). pp. 869-876. ISSN 2583-049X

Text Forecasting Silver Prices Using the Long Short-Term Memory (LSTM) Method.pdf Download (688kB)

Abstract

Silver is a versatile metal with numerous applications in human life, including industrial materials, ornaments, and investment assets. It serves as an alternative investment option due to its lower price compared to gold and its potential for value appreciation under specific market conditions. Historically stable, silver prices experienced a decline following the COVID-19 pandemic. Consequently, this study aims to forecast silver price trends to determine whether they will recover and stabilize. The forecasting is conducted using the Long Short-Term Memory (LSTM) method for a three-month period, from January 2023 to March 2023. The model’s performance is evaluated using the Mean Absolute Percentage Error (MAPE), with the best-obtained MAPE value being 0.0547. The forecasting results indicate that silver prices will experience a brief decline before rebounding.

Item Type:	Article
Subjects:	Q Science > QA Mathematics
Divisions:	Fakultas Matematika dan Ilmu Pengetahuan Alam (FMIPA) > Prodi Matematika
Depositing User:	DIAN KURNIASARI
Date Deposited:	21 Apr 2025 03:33
Last Modified:	21 Apr 2025 03:33
URI:	http://repository.lppm.unila.ac.id/id/eprint/54482

Actions (login required)

View Item