Scopus

Gold Price Forecasting in Vietnam: Leveraging Machine Learning Techniques

Năm XB 2026 Tạp chí / Hội thảo Advances in Information and Communication Technology: Proceedings of the 4th International Conference, ICTA 2025, Volume 1 Đơn vị ICTU DOI / Link https://doi.org/10.1007/978-3-032-18162-6_48 ↗

Tác giả

Tóm tắt

Gold has long been considered a safe investment asset, especially during times of financial, economic, and political instability. To help investors plan future strategies, this research aims to build machine learning models to predict gold prices in Vietnam using data from 2010 to 2024, which incorporates a variety of macroeconomic and geopolitical factors. We applied the traditional ARIMA(SARIMAX) model as well as deep learning models such as Long Short-Term Memory (LSTM), Convolutional Neural Network (CNN) and Convolutional Recurrent Neural Network (CRNN) to predict gold price in the vietnamese market. The results show that SARIMAX achieved worse predictive accuracy compared to deep learning models, with the LSTM model performing the best. We further improved the SARIMAX by combining it with deep learning models using the stacking method, incorporating two meta learning models: Linear Regression and XGBoost. Experimental results found that the hybrid model using XGBoost outperformed the one using linear meta model. Thus, by significantly improving the results, this hybrid model outperformed both SARIMAX and deep learning models. In summary, the application of Machine Learning and Artificial Intelligence algorithms in our research will bring clear benefits to investors and managers in making more accurate and effective gold investment decisions in the future.

Tài liệu tham khảo

[1] Yang, X.: The Prediction of Gold Price Using ARIMA Model (Jan. 2019). https://www.atlantis-press.com/proceedings/ssphe-18/55911762, Accessed 29 Jun. 2025

[2] Tripurana, N., Kar, B., Chakravarty, S., Paikaray, B.K., Satpathy, S.: Gold Price Prediction Using Machine Learning Techniques

[3] Dương T.T.T., Anh P.: Khái lược nghiên cứu vê ửng dụng các kỹ thuật mô hình học máy trong dự báo giá vàng

[4] Toàn T.N.V., Giúp T.D.V.: Dự báo giá vàng Việt Nam sử dụng mô hình Garch. Tạp chí Khoa học - Trường Đại học Cửu Long (2), Art. no. 2 (2016)

[5] Prediction of gold price with ARIMA and SVM - IOPscience. https://iopscience.iop.org/article/https://doi.org/10.1088/1742-6596/1767/1/012022, Accessed 29 Jun. 2025

[6] Siami-Namini, S., Namin, A.S.: Forecasting Economics and Financial Time Series: ARIMA vs. LSTM,” Mar. 16 (2018). arXiv: https://doi.org/10.48550/arXiv.1803.06386

[7] Alabdulrazzaq, H., Alenezi, M.N., Rawajfih, Y., Alghannam, B.A., Al-Hassan, A.A., Al-Anzi, F.S.: On the accuracy of ARIMA based prediction of COVID-19 spread. Results Phys. 27, 104509 (2021). https://doi.org/10.1016/j.rinp.2021.104509

[8] Gbadamosi, S.: Exploring the effectiveness of a multilayer neural network model for gold price prediction. Electrotech. Rev. 1(3), 159–163 (2024). https://doi.org/10.15199/48.2024.03.28

[9] Wang, S., Li, C, Lim, A.: Why Are the ARIMA and SARIMA not Sufficient, 02 Mar. (2021) https://doi.org/10.48550/arXiv.1904.07632

[10] Khoa T. A.: Các yếu tố tác động đến giá vàng trên thị trường Việt nam,” Tạp chí Khoa học và Đào tạo Ngân hàng (nay là Tạp chí Kinh tế - Luật và Ngân hàng), no. 176+177, Art. no. 176+177 (Jan. 2017)

[11] ul Sami, I., Junejo, K.N.:  Predicting future gold rates using machine learning approach. Inter. J. Adv. Comput. Sci. Appli. 8(12), Art. no. 12, https://doi.org/10.14569/IJACSA.2017.081213

[12] Desai, S., Vojtko, R., Cisár, D.: Insights from the Geopolitical Sentiment Index made with Google Trends,” Social Science Research Network, Rochester, NY: 4948780. https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4948780, Accessed 29 Jun. 2025

[13] Zelieska, L., Vojtko, R., Dujava, C.: Can Google Trends Sentiment Be Useful as a Predictor for Cryptocurrency Returns?. Social Science Research Network, Rochester, NY: 4806394. https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4806394, Accessed 29 Jun. 2025

[14] A Survey of Ensemble Learning: Concepts, Algorithms, Applications, and Prospects

IEEE Journals & Magazine

IEEE Xplore. https://ieeexplore.ieee.org/document/9893798, Accessed 29 Jun. 2025

[15] Chae, S., Bae, S.J:. Bayesian Hyper-parameter Optimization in One-dimensional Convolutional Autoencoder for Monitoring Bearing Health Status. https://doi.org/10.57062/ijpem-st.2023.0115

[16] Streeter, M.: Bayes Optimal Early Stopping Policies for Black-Box Optimization, 21 Feb. (2019). https://doi.org/10.48550/arXiv.1902.08285

[17] Alhebaishi, E., Krupasindhu Panigrahi, S.: Is gold a safe heaven? evidence from time series forecasting using sarimax model. In: 2023 International Conference on Sustainable Islamic Business and Finance (SIBF), pp. 136–141 (Sep. 2023). https://doi.org/10.1109/SIBF60067.2023.10379916

[18] Modeling and Forecasting Daily Hotel Demand: A Comparison Based on SARIMAX, Neural Networks, and GARCH Models. https://www.mdpi.com/2571-9394/3/3/37, Accessed 29 Jun 2025

[19] Long Short-Term Memory

MIT Press Journals & Magazine

IEEE Xplore. Ahttps://ieeexplore.ieee.org/abstract/document/6795963, Accessed 29 Jun. 2025

[20] Share Price Trend Prediction Using CRNN with LSTM Structure: Smart Science, vol 7(3). https://www.tandfonline.com/doi/abs/,  https://doi.org/10.1080/23080477.2019.1605474, Accessed: 29 Jun. 2025

[21] Time series forecasting: problem of heavy-tailed distributed noise

International Journal of Advances in Engineering Sciences and Applied Mathematics. https://link.springer.com/article/https://doi.org/10.1007/s12572-021-00312-x, Accessed 29 Jun. 2025

Ghi chú

Source ID: 145; Author classification: ICTU - Main Author; First listed author: Vu Xuan Nam; Contact author: Cong Doan Truong; Total authors: 5; Not found in provided Springer books 10.1007/978-3-032-18159-6 or 10.1007/978-3-032-18316-3
← Quay lại danh sách bài báo