Perbandingan Kinerja Model ARIMA dan LSTM pada Multi-Horizon Forecasting Harga Emas dengan Evaluasi Mean Directional Accuracy
-
Muhamad Prasetyo Bayu Aji
*
Universitas Muhammadiyah Surakarta, Surakarta,
Indonesia
- Aris Rakhmadi Universitas Muhammadiyah Surakarta, Surakarta, Indonesia (*) Corresponding Author
Abstract
Precious metals, particularly gold, represent one of the most sought-after value-preserving investment instruments, yet their dynamic price fluctuations present significant challenges, making gold a difficult-to-predict yet crucial asset for investment decision-making. This study aims to forecast gold prices by comparing the performance of Autoregressive Integrated Moving Average (ARIMA) and Long Short-Term Memory (LSTM) forecasting models through three testing scenarios: single-step, multi-step forecasting, and rolling forecasting. This study utilizes 40 years of historical gold price data obtained from the public source Kaggle. The ARIMA model was implemented on stationary data, while LSTM was optimized with additional lag, volatility, and momentum features. Experimental results indicate that in the single-step scenario, both models produced equivalent accuracy with a MAPE below 1%. In the multi-step scenario, LSTM significantly outperformed ARIMA with a MAPE of 1.89% compared to 3.54%. In the rolling scenario, LSTM again performed better with a MAPE of 1.83% versus 3.52% for ARIMA. Conversely, ARIMA consistently recorded higher Mean Directional Accuracy (MDA) values across all scenarios, reaching 57.30% in the rolling forecast compared to LSTM's 46.07%, indicating ARIMA's advantage in identifying trend direction. This study concludes that the LSTM approach is more optimal for achieving numerical prediction precision over medium-term horizons, while the statistical ARIMA method is more reliable for accurately projecting market movement direction.
Downloads
References
A. Syauqi and I. Yusuf, “Analisis Investasi Syariah Melalui Logam Mulia ( Di Toko Emas Melati Kebun Sayur Balikpapan ),” Bridg. J. Islam. Digit. Econ. Manag., vol. 1, no. 1, pp. 304–311, 2024, [Online]. Available: https://journal.alshobar.or.id/index.php/bridging
B. Heradhyaksa, “Implementasi Investasi Emas Syariah Perspektif Hukum Islam,” J. Huk. Ekon. Islam, vol. 6, no. 1, pp. 35–51, 2022, [Online]. Available: https://jhei.appheisi.or.id/index.php/jhei/article/download/111/60
Z. S. Putri and N. Nur’aeni, “Analisis Fluktuasi Harga Emas dan Tingkat Inflasi terhadap Pendapatan Gadai Emas Syariah di Bank Syariah Mandiri,” Indones. J. Econ. Manag., vol. 1, no. 3, pp. 489–498, 2021, doi: 10.35313/ijem.v1i3.3491.
H. Imaduddin, S. Agrippina, A. Yusuf, and M. S. Adhantoro, “A Robust Model for Early Detection of Chronic Kidney Disease Leveraging Machine Learning and Data Balancing Techniques,” Bull. Electr. Eng. Informatics, vol. 15, no. 2, pp. 1442–1451, 2026, doi: 10.11591/eei.v15i2.11247.
A. Zulfahrizan, M. Alby Savana HSB, S. Putra Paskah Halawa, and F. Ramadhani, “Penerapan Model Hybrid Machine Learning Arima-Lstm (Long Short-Term Memory) Dalam Prediksi Harga Emas 5 Tahun Ke-Depan,” JATI (Jurnal Mhs. Tek. Inform., vol. 9, no. 4, pp. 5737–5741, 2025, doi: 10.36040/jati.v9i4.13914.
S. Nendi, P. P. Harjono, and H. Rizki, “Prediksi Penjualan Aerosol Menggunakan Algoritma ARIMA ,” INSOLOGI J. Sains dan Teknol., vol. 4, no. 1, pp. 113–126, 2025, doi: 10.55123/insologi.v4i1.4868.
A. M. Zebada and E. W. Pamungkas, “Analysis of A Deep Learning Algorithm for Fracture Detection in X-Ray Images,” Int. J. Adv. Data Inf. Syst., vol. 6, no. 3, pp. 716–734, 2025, doi: 10.59395/ijadis.v6i3.1451.
F. Fauzi, S. Aulia, A. R. Syaifullah, and T. W. Utami, “Peramalan Harga Emas Menggunakan Pendekatan Long-Short Term Memory (LSTM),” J. Edukasi dan Penelit. Inform., vol. 10, no. 2, p. 252, 2024, doi: 10.26418/jp.v10i2.78332.
I. G. T. Suryawan, K. N. Putra, P. M. Meliana, and I. G. I. Sudipa, “Performance Comparison of ARIMA , LSTM , and Prophet Methods in Sales Forecasting,” Sink. J. dan Penelit. Tek. Inform., vol. 8, no. October, pp. 2410–2421, 2024, doi: 10.33395/sinkron.v8i4.14057.
K. N. Khikmah and A. Sofro, “Perbandingan Kinerja Model ARIMA dan LSTM untuk Peramalan Curah Hujan di Kalimantan Tengah,” J. Ris. dan Apl. Mat., vol. 9, no. 2, pp. 199–207, 2025, [Online]. Available: journal.unesa.ac.id/index.php/jram
K. Umam and Ardiansyah, “Perbandingan Metode ARIMA dan LSTM pada Prediksi Jumlah Pengunjung Perpustakaan,” MIND (Multimedia Artif. Intell. Netw. Database) J., vol. 8, no. 2, pp. 119–129, 2023, doi: https://doi.org/10.26760/mindjournal.v8i2.119-129.
D. G. Taslim and I. M. Murwantara, “Comparative Analysis of ARIMA and LSTM for Predicting Fluctuating Time Series Data,” Bull. Electr. Eng. Informatics, vol. 13, no. 3, pp. 1943–1951, 2024, doi: 10.11591/eei.v13i3.6034.
Y. R. Madhika, Kusrini, and T. Hidayat, “Gold Price Prediction Using the ARIMA and LSTM Models,” Sink. J. dan Penelit. Tek. Inform., vol. 7, no. 3, pp. 1255–1264, 2023, doi: 10.33395/sinkron.v8i3.12461.
B. Arham, Sukasih, and R. Sani, “Prediksi Harga Emas Harian dan Multi-Horizon Menggunakan ARIMA, LSTM dan Model Hybrid ARIMA-LSTM,” J. Sains Inform. Terap., vol. 5, no. 1, pp. 18–23, 2026, doi: 10.62357/joseamb.v2i2.
C. Tian, Y. Bai, R. Tansuchat, and S. Sriboonchitta, “Nonlinear State Estimation with Deep Learning for Financial Forecasting : An EKF-LSTM Hybrid Approach with Cross-Market Evidence,” Economies, vol. 14, no. 5, pp. 1–31, 2026, doi: 10.3390/economies14050184.
H. A. Nabila and E. W. Pamungkas, “Perbandingan Algortima Machine Learning: SVM, Random Forest, dan XGBoost untuk Prediksi Stroke,” RABIT J. Teknol. dan Sist. Inf. Univrab, vol. 10, no. 2, pp. 1098–1110, 2025, doi: https://doi.org/10.36341/rabit.v10i2.6444.
D. N. Fadhilah, K. Parmikanti, and B. N. Ruchjana, “Peramalan Return Saham Subsektor Perbankan Menggunakan Model ARIMA-GARCH,” J. FOURIER, vol. 13, no. 1, pp. 1–19, 2024, doi: 10.14421/fourier.2024.131.1-19.
A. D. Milniadi and N. O. Adiwijaya, “Analisis Perbandingan Model Arima Dan Lstm Dalam Peramalan Harga Penutupan Saham ( Studi Kasus : 6 Kriteria Kategori Saham Menurut Peter Lynch),” Sibatik J., vol. 2, no. 6, 2023, doi: 10.54443/sibatik.v2i6.798.
P. S. T. P. Purnama, “Optimizing Bitcoin Price Prediction with LSTM : A Comprehensive Study on Feature Engineering and the April 2024 Halving Impact,” Elinvo (Electronics, Informatics, Vocat. Educ., vol. 9, no. 1, pp. 165–177, 2024, doi: 10.21831/elinvo.v9i1.72518.
C. Cheng, C. Li, and G. Weng, “An Improved LSTM-Based Approach for Stock Price Volatility Prediction with Feature Selection Optimization,” Artif. Intell. Mach. Learn. Rev., pp. 1–15, 2023, doi: 10.69987/AIMLR.2023.40101.
D. N. Rathnayake, O. Alele, and P. A. Louembe, “Empirical study on the volatility spillover effect of gold , silver and platinum prices,” Financ. Stat. J., vol. 8, no. 1, pp. 1–19, 2025, doi: 10.24294/fsj9514.
Y. S. Priyambudi, Zulfikar Setyo Nugroho, “An Implementation of Normalization to Predict Student Performance,” AIP Conf. Proc., vol. 2926, no. 1, 2024, doi: https://doi.org/10.1063/5.0182879.
Nilasari, R. E. Saputro, and G. Karyono, “Perbandingan Model LSTM dan Temporal Fusion Transformer untuk Prediksi Harga Emas,” Build. Informatics, Technol. Sci., vol. 7, no. 4, pp. 2811–2820, 2026, doi: 10.47065/bits.v7i4.8204.
Y. B. Caesar, K. Hadiono, and E. Ardhianto, “Evaluasi Empiris Model ARIMA dan LSTM dalam Konteks Peramalan Penjualan Mobil Toyota,” AITI J. Teknol. Inf., vol. 22, no. 2, pp. 221–235, 2025, doi: https://doi.org/10.24246/aiti.v22i2.221-235.
A. L. Schaffer, T. A. Dobbins, and S.-A. Pearson, “Interrupted Time Series Analysis Using Autoregressive Integrated Moving Average ( ARIMA ) Models : a Guide for Evaluating Large-scale Health Interventions,” BMC Med. Res. Methodol., vol. 21, no. 58, pp. 1–12, 2021, doi: https://doi.org/10.1186/s12874-021-01235-8.
R. M. Sujarwo, “Penerapan Model Arima untuk Memproyeksi Tren Harga TBS Sawit di Provinsi Jambi,” Sci. J. Reflect. Econ. Accounting, Manag. Bus., vol. 8, no. 1, pp. 251–261, 2025, doi: 10.37481/sjr.v8i1.1040.
H. Thamrin and M. Nu’man Normas, “Analyzing and Forecasting Admission Data using Time Series Model,” JOIN (Jurnal Online Inform., vol. 5, no. 1, pp. 35–44, 2020, doi: 10.15575/join.v5i1.546.
M. N. A. Simanjuntak, R. Tipani, Z. M. Afriyanti, Indriyanto, and N. Hidayati, “Peramalan Jumlah Kedatangan Jalur Udara di Bandara Depati Amir Menggunakan Model Arima,” J. Fraction, vol. 3, no. 2, pp. 44–52, 2023, doi: 10.33019/fraction.v3i2.45.
R. J. Hyndman and G. Athanasopoulos, Forecasting: Principles and Practice (3rd ed). Melbourne, Australia: OTexts, 2021. [Online]. Available: OTexts.com/fpp3
W. N. W. M. Din and N. Shaadan, “Application of Functional Time Series Model in Forecasting Monthly Diurnal Maximum API Curves : A Comparison between Multi- Step Ahead and Iterative One-Step Ahead Approach,” Malaysian J. Fundam. Appl. Sci., vol. 18, no. 2, pp. 124–137, 2022, doi: 10.11113/mjfas.v18n1.2435.
M. N. Ulwan, Danardono, and A. Azwar, “Peramalan Penerimaan Iuran Program Jaminan Kehilangan Pekerjaan BPJS Ketenagakerjaan Menggunakan Metode Hybrid Prophet -BiLSTM,” J. Jamsostek, vol. 3, no. 2, pp. 174–201, 2025, doi: 10.61626/jamsostek.v3i2.123.
H. Hewamalage, C. Bergmeir, and K. Bandara, “Recurrent Neural Networks for Time Series Forecasting: Current Status and Future Directions,” Int. J. Forecast., vol. 37, no. 1, pp. 388–427, 2021, doi: 10.48550/arXiv.1909.00590.
M. F. Dixon, I. Halperin, and P. Bilokon, Machine Learning in Finance. Cham, Switzerland: Springer, 2020. doi: 10.1007/978-3-030-41068-1.
S. Somisetti and G. P. Manla, “Multi-Model Ensemble Approach for Stock Price Forecasting : An Interactive Dashboard Implementation Using ARIMA , Prophet , and LSTM Models with Advanced Trading Strategy Integration,” Vellore Institute of Technology, Amaravathi (VIT-AP University), 2025. doi: https://doi.org/10.36227/techrxiv.175322805.53639971/v1.
M. E. Putra and T. Oktavia, “Comparative Analysis of Temporal Fusion Transformer and Long Short- Term Memory Architecture Resilience in Predicting Solana Price Volatility Across Different Market Phases,” J. Tek. Inform., vol. 7, no. 3, pp. 2935–2943, 2026, doi: 10.52436/1.jutif.2026.7.3.5894.
Bila bermanfaat silahkan share artikel ini
Berikan Komentar Anda terhadap artikel Perbandingan Kinerja Model ARIMA dan LSTM pada Multi-Horizon Forecasting Harga Emas dengan Evaluasi Mean Directional Accuracy
Pages: 611-622
Copyright (c) 2026 Muhamad Prasetyo Bayu Aji, Aris Rakhmadi
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under Creative Commons Attribution 4.0 International 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 (Refer to The Effect of Open Access).
