Peramalan Harga Emas 2015-2019 Menggunakan LSTM Berbasis Harga Penutupan Harian
DOI:
https://doi.org/10.29407/64qgrc58Keywords:
Directional Statistic, Forecasting, Harga Emas, LSTMAbstract
Sebagai aset safe haven, emas memegang peran krusial dalam strategi investasi dan manajemen risiko, sehingga akurasi peramalan harganya menjadi sangat penting. Penelitian ini menerapkan algoritma Long Short-Term Memory (LSTM) untuk memproyeksikan harga emas harian menggunakan data historis penutupan (closing price) periode 2015 hingga 2019. Melalui pendekatan univariat, data diproses dengan teknik normalisasi dan windowing sebelum tahap pelatihan model. Berdasarkan evaluasi kinerja, model menunjukkan akurasi tinggi dalam mengestimasi nominal harga, tercermin dari nilai Mean Squared Error (MSE) sebesar 0,00108 dan Mean Absolute Percentage Error (MAPE) 3,54%. Namun, terdapat kesenjangan menarik pada prediksi arah tren, di mana Directional Statistic (DS) hanya mencapai 46,33%. Hal ini mengindikasikan bahwa meskipun LSTM univariat sangat andal memprediksi besaran angka, model ini masih kesulitan menangkap momentum naik-turunnya pasar secara presisi. Oleh karena itu, penelitian selanjutnya disarankan mengintegrasikan variabel eksternal agar model lebih sensitif terhadap dinamika arah pergerakan harga.
Downloads
References
[1] D. N. Ahsanah, “EMAS SEBAGAI INSTRUMEN INVESTASI JANGKA PANJANG,” Jurnal Kajian Ekonomi Hukum Syariah, vol. 8, no. 1, hlm. 177–187.
[2] A. Amini dan R. Kalantari, “Gold price prediction by a CNN-Bi-LSTM model along with automatic parameter tuning,” PLoS One, vol. 19, no. 3 March, Mar 2024, doi: 10.1371/JOURNAL.PONE.0298426.
[3] W. Gong, “Research on gold price forecasting based on lstm and linear regression,” SHS Web of Conferences, vol. 181, hlm. 02005, 2024, doi: 10.1051/shsconf/202418102005.
[4] “Al-Selwi et al., 2024”.
[5] M. Aziiz Irwansyah, A. Triana, E. Darmayanti Simanullang, Y. Nur Alinda, dan A. Ibrahim, “PREDIKSI HARGA DAN VOLATILITAS EMAS DUNIA HARIAN: PERBANDINGAN MODEL GARCH DAN LONG SHORT-TERM MEMORY,” 2025.
[6] T. G. Lasijan, R. Santoso, dan A. R. Hakim, “PREDIKSI HARGA EMAS DUNIA MENGGUNAKAN METODE LONG-SHORT TERM MEMORY,” Jurnal Gaussian, vol. 12, no. 2, hlm. 287–295, Jul 2023, doi: 10.14710/j.gauss.12.2.287-295.
[7] W. M. P. Dhuhita, M. F. Farid, A. Yaqin, Haryoko, dan A. A. Huda, 2023 International Conference on Informatics, Multimedia, Cyber and Informations System. IEEE, 2023.
[8] W. Cahyo Utomo dan M. Aris Saputra, “Forecasting Pergerakan Harga Volatility Index dengan Menggunakan Metode Fuzzy Tsukamoto dan Evaluasi Dstat Metric.”
[9] B. Gülmez, “Stock price prediction with optimized deep LSTM network with artificial rabbits optimization algorithm,” Expert Syst Appl, vol. 227, Okt 2023, doi: 10.1016/j.eswa.2023.120346.
[10] J. Khatib Sulaiman, S. Handayani, D. Toresa, dan U. Lancang Kuning, “Convolutional Neural Network – Long Short Term Memory Untuk Prediksi Harga Emas Indonesia,” The Indonesian Journal of Computer Science, vol. 11, no. 3, Des 2022, doi: 10.33022/IJCS.V11I3.3074.
[11] M. R. Nurhambali, Y. Angraini, dan A. Fitrianto, “Implementation of Long Short-Term Memory for Gold Prices Forecasting,” Malaysian Journal of Mathematical Sciences, vol. 18, no. 2, hlm. 399–422, 2024, doi: 10.47836/MJMS.18.2.11.
[12] H. Yan, “Research on Gold Price Prediction Based on LSTM Modeling,” Advances in Economics, Management and Political Sciences, vol. 94, no. 1, hlm. 202–210, Okt 2024, doi: 10.54254/2754-1169/94/2024ox0166.
[13] R. N. Adila dan R. N. Adila, “Peramalan Harga Emas Menggunakan Metode Long Short Term Memory (LSTM) dan ARIMAX,” 2024.
[14] T. Hidayah, “Perbandingan Algoritma Long Short-Term Memory (LSTM) dan Gated Recurrent Unit (GRU) untuk Prediksi Harga Emas Dunia.”
[15] Javatpoint, “Long Short-Term Memory (LSTM).”
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Erwin Setiawan, Resty Wulaningrum
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Copyright on any article is retained by the author(s).
- The author grants the journal, right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment 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 acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
- The article and any associated published material is distributed under the Creative Commons Attribution-ShareAlike 4.0 International License
