Comparative Modeling of Naïve Bayes and LSTM with Monte Carlo Forecasting for Silver Prices
DOI:
https://doi.org/10.31937/ti.v17i2.4493Abstract
Volatilitas harga perak dalam beberapa tahun terakhir, terutama sejak 2023, yang didorong oleh lonjakan permintaan di sektor energi terbarukan, telah meningkatkan kompleksitas prediksi menggunakan pendekatan konvensional. Studi ini menguji dua pendekatan yang berbeda secara filosofis: Naïve Bayes (NB), yang mengandalkan asumsi independensi fitur, dan Long Short-Term Memory (LSTM), yang secara eksplisit dirancang untuk menangkap dependensi temporal. Menggunakan data harga perak harian (USD/troy ons) dari Investing.com untuk periode Januari 1989–Oktober 2025, NB diimplementasikan dengan tiga fitur lag (t−1 hingga t−3), sementara LSTM menggunakan arsitektur dua lapis (50 unit), 0,2 dropout, dan jendela sekuensial 60 hari. Hasil menunjukkan bahwa LSTM menghasilkan prediksi yang lebih responsif terhadap titik balik, meskipun RMSE-nya (1,0222) sedikit lebih tinggi daripada NB (0,9888). Fenomena ini sebenarnya mencerminkan sensitivitas LSTM terhadap volatilitas ekstrem di akhir tahun 2025 (>USD 53/oz), bukan kegagalan model. Sebaliknya, NB cenderung terlalu halus (over-smooth), sehingga mengakibatkan deviasi sistematis ketika tren berbalik. Dengan MAE 0,7002 (vs. 0,7354) dan stabilitas pola prediksi yang lebih realistis, LSTM direkomendasikan sebagai kerangka kerja utama, terutama jika dikombinasikan dengan estimasi ketidakpastian melalui simulasi Monte Carlo.
Downloads
Additional Files
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Muhammad Azmi Alauddin, Firda Fadri, Muhammad Amjad Munjid

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution-ShareAlike International License (CC-BY-SA 4.0) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
Copyright without Restrictions
The journal allows the author(s) to hold the copyright without restrictions and will retain publishing rights without restrictions.
The submitted papers are assumed to contain no proprietary material unprotected by patent or patent application; responsibility for technical content and for protection of proprietary material rests solely with the author(s) and their organizations and is not the responsibility of the ULTIMATICS or its Editorial Staff. The main (first/corresponding) author is responsible for ensuring that the article has been seen and approved by all the other authors. It is the responsibility of the author to obtain all necessary copyright release permissions for the use of any copyrighted materials in the manuscript prior to the submission.












