A hybrid machine learning and long short-term memory approach for gold price prediction to support strategic decision-making in the bullion business
DOI:
https://doi.org/10.61511/dynames.v3i1.3458Keywords:
bullion business, decision-support system, gold price forecasting, hybrid machine learning, long short-term memoryAbstract
Background: Gold price volatility presents a strategic challenge for the bullion business, particularly for institutions such as Pegadaian, where pricing accuracy directly affects gold savings products, pawn valuation, inventory planning, and risk exposure. Previous studies indicate that traditional forecasting models struggle to capture long-term temporal dependencies, while deep learning models often lack interpretability. This study aims to address this gap by developing a forecasting framework that balances predictive accuracy with business-oriented interpretability. Methods: This study applies a quantitative experimental design using 5,391 daily gold price observations from 2004 onward. Feature engineering incorporates lagged prices, moving averages, and rolling volatility indicators. Random Forest and Extreme Gradient Boosting models are employed to model nonlinear relationships and extract feature importance, while a Long Short-Term Memory (LSTM) network captures long-term temporal dependencies through sequential learning. Model performance is evaluated using Mean Absolute Error, Root Mean Squared Error, and Mean Absolute Percentage Error. Findings: The results demonstrate that the LSTM model significantly outperforms ensemble-based machine learning models, achieving the lowest forecasting error with a Mean Absolute Percentage Error of 2.27%. Feature importance analysis identifies recent price ranges and moving averages as dominant predictors, confirming trend-based behavior in gold price movements. Conclusion: The proposed hybrid framework delivers accurate and interpretable gold price forecasts applicable to business-oriented decision support in the bullion industry. Within this framework, LSTM serves as the primary forecasting engine for capturing temporal dependencies, while Random Forest and XGBoost provide interpretable insights through feature importance analysis. Novelty/Originality of this article: This study introduces a decision-oriented hybrid framework integrating deep learning-based temporal modeling with interpretable machine learning for strategic applications in bullion-based financial institutions.
References
Ahmad, M., Khan, S., Ahmad, R. W., Rehman, A. A., & Khan, R. (2025). Comparative analysis of statistical and machine learning models for gold price prediction. Journal of Media Horizons, 6(4), 50–65. https://doi.org/10.5281/zenodo.17062124
Amryliana, S., Bahri, S., & Alfian, M. R. (2025). Optimization of long short term memory model for gold price prediction using adaptive moment estimation optimasi model long short term memory untuk memprediksi harga emas menggunakan adaptive moment estimation. Jurnal Matematika, Statistika Dan Komputasi, 21(3), 669–683. https://doi.org/10.20956/j.v21i3.42872
Bareth, R., Yadav, A., Gupta, S., & Pazoki, M. (2024). Daily average load demand forecasting using LSTM model based on historical load trends. IET Generation, Transmission &Distribution, January, 952–962. https://doi.org/10.1049/gtd2.13132
Barreñada, L., Dhiman, P., Timmerman, D., Boulesteix, A. L., & Calster, B. Van. (2024). Understanding overfitting in random forest for probability estimation : a visualization and simulation study. Diagnostic and Prognostic Research, 1–14. https://doi.org/10.1186/s41512-024-00177-1
Bichri, H., Chergui, A., & Hain, M. (2024). Investigating the Impact of Train / Test Split Ratio on the Performance of Pre-Trained Models with Custom Datasets. (IJACSA) International Journal of Advanced Computer Science and Applications, 15(2), 331–339. https://doi.org/10.14569/IJACSA.2024.0150235
Changani, J. (2024). Factors Influencing Gold Price Movements : A Time Series Analysis Perspective. SSRN Electronic Journal. https://doi.org/10.2139/ssrn.4815102
Chen, T., & Guestrin, C. (2016). XGBoost: A Scalable Tree Boosting System. In Proceedings of the 22nd Acm Sigkdd International Conference on Knowledge Discovery and Data Mining, 785–794. https://doi.org/10.1145/2939672.2939785
Elebe, O., Imediegwu, C. C., & Filani, O. M. (2022). Predictive Financial Modeling Using Hybrid Deep Learning Architectures. International Journal of Multidisciplinary Research and Growth Evaluation, 3(2), 859–872. https://doi.org/10.54660/.IJMRGE.2022.3.2.859-872
Fadillah, Suhud, U., & Rizan, M. (2025). Analysis of Brand Trust , Service Quality , and Price on Purchase Decisions and Customer Loyalty in Gold Bullion Investment at PT . Pegadaian : The Moderating Role of Customer Satisfaction. Green International Journal of Tourism and Management, 3(1), 89–99. https://doi.org/10.38035/gijtm.v3i1
Fozap, F. M. P. (2025). Hybrid Machine Learning Models for Long-Term Stock Market Forecasting : Integrating Technical Indicators. Journal of Risk and Financial Management, 18(201). https://doi.org/10.3390/jrfm18040201
Gadage, N. G., & Baporikar, I. U. (2025). Survey on Different Methods of Machine Learning Models used to Predict the Price of Gold. Journal Of Technical Education, 48(1), 314.
Gamage, A. N. K. K. (2025). Research Design, Philosophy, and Quantitative Approaches in Scientific Research Methodology. Scholars Journal of Engineering and Technology, 13(2), 91–103. https://doi.org/10.36347/sjet.2025.v13i02.004
Gbadamosi, S. L., Nwulu, N. I., & Akinola, S. O. (2024). Exploring the effectiveness of a multilayer neural network model for gold price prediction. PRZEGLĄD ELEKTROTECHNICZNY, 3, 0–1. https://doi.org/10.15199/48.2024.03.28
Hochreiter, S., & Schmidhuber, J. (1997). Long Short-Term Memory. Neural Computation, 9(8), 1735–1780. https://doi.org/10.1162/neco.1997.9.8.1735
Jakobs, M., & Saadallah, A. (2023). Explainable Adaptive Tree-based Model Selection for Time-Series Forecasting. Proceedings - IEEE International Conference on Data Mining, ICDM, 180–189. https://doi.org/10.1109/ICDM58522.2023.00027
Kong, X., Chen, Z., Liu, W., Ning, K., Zhang, L., Muhammad Marier, S., Liu, Y., Chen, Y., & Xia, F. (2025). Deep learning for time series forecasting: a survey. International Journal of Machine Learning and Cybernetics, 16(7–8), 5079–5112. https://doi.org/10.1007/s13042-025-02560-w
Krichen, M., & Mihoub, A. (2025). Long Short-Term Memory Networks : A Comprehensive Survey. AI, 1–21. https://doi.org/10.3390/ai6090215
Kyriazos, T., & Poga, M. (2024). Application of Machine Learning Models in Social Sciences : Managing Nonlinear Relationships. Encyclopedia, 1790–1805. https://doi.org/10.3390/encyclopedia4040118
Laska, R. R., & Yolanda, A. M. (2024). A Comparative Study of Z-Score and Min-Max Normalization for Rainfall Classification in Pekanbaru. Journal of Data Science, 2024(April). http://ipublishing.intimal.edu.my/jods.html
Li, L., Huang, X., Yan, C., He, S., Cheng, S., & Yang, W. (2025). Evaluation of predictive performance of modeling hyperuricemia using medical big data : comparison of data preprocessing methods. Journal of Big Data, 12(80). https://doi.org/10.1186/s40537-025-01142-5
Little, C. O., Lina, D. H., & Allen, G. I. (2023). Fair Feature Importance Scores for Interpreting Tree-Based Methods and Surrogates. ArXiv, 1–28. http://arxiv.org/abs/2310.04352
Ma, X., & Fan, S. (2024). Research on Cross-national Customer Churn Prediction Model for Biopharmaceutical Products Based on LSTM-Attention Mechanism. Academia Nexus Journal, 3(3), 1–22. https://academianexusjournal.com
Majumdar, P. (2025). The Accuracy-Interpretability Dilemma : A Strategic Framework for Navigating the Trade-off in Modern Machine Learning. American Journal of Information Science and Technology, 9(3), 211–224. https://doi.org/10.11648/j.ajist.20250903.15
Maryati, I., & Paramita, A. S. (2023). Gold Prices Time-Series Forecasting : Comparison of Statistical Techniques. Journal of Applied Data Sciences, 4(4), 372–381. https://doi.org/10.47738/jads.v4i4.135
Nazir, Z., Zarymkanov, T., & Park, J. (2022). A Machine Learning Model Selection considering Tradeoffs between Accuracy and Interpretability. Advances in Science, Technology and Engineering Systems Journal, 7(4), 72–78. https://doi.org/10.25046/aj070410
Novandraanugrah. (2024). XAU/USD gold price historical data (2004–2024) [Data set]. https://www.kaggle.com/datasets/novandraanugrah/xauusd-gold-price-historical-data-2004-2024
Ogundu, P. G. (2025). Economic Policies, Financial Markets, and Global Currency Dynamics Shaped by US Trade Tensions. International Journal of Research Publication and Reviews, 6(1), 4819–4831. https://doi.org/10.55248/gengpi.6.0125.0641
Pala, S. K. (2023). Role and importance of predictive analytics in financial market risk assessment. International Journal of Enhanced Research in Management & Computer Applications, 12(8), 95–100. https://www.erpublications.com/uploaded_files/download/sravan-kumar-pala_DKvhh.pdf
Pandit, S., & Luo, X. (2025). A novel prediction model to evaluate the dynamic interrelationship between gold and crude oil. International Journal of Data Science and Analytics, 20(2), 1161–1182. https://doi.org/10.1007/s41060-024-00519-8
Pennacchio, A., Giampaolo, F., Cafaro, V., Cicatiello, P., Della, B., Giardina, P., Rosanova, R., Savoia, M., Velotta, R., Piccialli, F., & Piscitelli, A. (2024). Sensors and Actuators : B . Chemical A bacterial biosensor based on gold nanoparticles functionalized by a hydrophobin-chimera and combined with machine learning for user-friendly detection. Sensors and Actuators: B. Chemical, 410, 135645. https://doi.org/10.1016/j.snb.2024.135645
Quang, P. D., & Thang, T. Q. (2025). Analysis and forecasting of daily global gold price : an SARIMA-LSTM approach with Random Forest technique. Cogent Economics & Finance, 13(1). https://doi.org/10.1080/23322039.2025.2568969
Rejeb, A., Rejeb, K., & Alnabulsi, K. (2023). Tracing Knowledge Diffusion Trajectories in Scholarly Bitcoin Research: Co-Word and Main Path Analyses. Journal Risk and Financial Managent, 16(8), 355. https://doi.org/10.3390/jrfm16080355
Rosenblatt, M., Tejavibulya, L., Noble, S., & Scheinost, D. (2024). Data leakage in fl ates prediction performance in connectome-based machine learning models. Nature Communications, 1–15. https://doi.org/10.1038/s41467-024-46150-w
Safriandono, A. N., Ignatius, D. R., Setiadi, M., Dahlan, A., Zakiyah, F., Wibisono, I. S., & Ojugo, A. A. (2024). Journal of Future Artificial Intelligence Analyzing Quantum Feature Engineering and Balancing Strategies Effect on Liver Disease Classification. Journal of Future Artificial Intelligence and Technologies, 1(1), 52–63. https://doi.org/10.62411/faith.2024-12
Salim, M., & Djunaidy, A. (2024). Development of a CNN-LSTM Approach with Images as Time- Development of a CNN-LSTM Approach with Images as Time- Series Data Representation for Predicting Gold Prices. Procedia Computer Science, 234, 333–340. https://doi.org/10.1016/j.procs.2024.03.007
Santoso, I. C. P., Dewantara, R., & Widhiawati, D. (2025). Legal Protection for Customers Related to the Minimum Transaction Limit for Gold Bullion Business. International Journal of Business, Law, and Education, 6(2), 1158–1169. https://ijble.com/index.php/journal/index
Sasikala, S., & Bhuvana, R. (2024). An enhanced study on gold price prognosis using machine learning. International Journal of Advanced Research in Science, Communication and Technology, 4(5), 1–7. https://doi.org/10.48175/IJARSCT-18401
Sezer, O. B., Gudelek, M. U., & Ozbayoglu, A. M. (2020). Financial time series forecasting with deep learning: A systematic literature review: 2005–2019. Applied Soft Computing Journal, 90, 2005–2019. https://doi.org/10.1016/j.asoc.2020.106181
Shafiee, S., & Topal, E. (2010). An overview of global gold market and gold price forecasting. Resources Policy, 35(3), 178–189. https://doi.org/10.1016/j.resourpol.2010.05.004
Song, D. (2024). Stock Price Prediction based on Time Series Model and Long Short-term Memory Method. Highlights in Business, Economics and Management Volume, 24, 1203–1210.
Vuong, P. H., & Phu, L. H. (2024). A bibliometric literature review of stock price forecasting : From statistical model to deep learning approach. SCIENCE PROGRESS, 107(1), 1–31. https://doi.org/10.1177/00368504241236557
Xie, B. (2025). Gold Price Forecast : A Summary of the Integration of Economic Factors and Calculation Methods. The International Conference on Data Science and Engineering Transform, ICDSE, 360–365. https://doi.org/10.5220/0013697400004670
Yang, Y. (2025). TCN-QV: an attention-based deep learning method for long sequence time-series forecasting of gold prices. PLOS ONE, 1–24. https://doi.org/10.1371/journal.pone.0319776
Zangana, H. M., & Obeyd, S. R. (2024). Deep Learning-based Gold Price Prediction: A Novel Approach using Time Series Analysis. Sistemasi: Jurnal Sistem Informasi, 13(6), 2581–2591. http://sistemasi.ftik.unisi.ac.id
Downloads
Published
How to Cite
Issue
Section
Citation Check
License
Copyright (c) 2026 Ririn Anugerah Ikasatya, Cahya Apriliani, Fathir Jannatul Firdaus
This work is licensed under a Creative Commons Attribution 4.0 International License.
