Volume 5 , Issue 2 , PP: 87-116, 2025 | Cite this article as | XML | Html | PDF | Full Length Article
Asifa Iqbal 1 * , Marwa M. Eid 2
Accurate forecasting of gold prices remains a critical challenge in financial markets due to the nonlinear, nonstationary, and regime-dependent nature of commodity price dynamics, particularly for gold quoted against the US dollar (XAU/USD), which plays a central role as a safe-haven asset, inflation hedge, and portfolio diversifier. Motivated by the growing limitations of traditional econometric and manually tuned machine learning approaches in handling long-horizon, multi-timeframe financial data, this study proposes a robust forecasting framework that integrates deep learning with metaheuristic optimization. The main contribution of this work lies in the systematic combination of a Deep Pyramid Recurrent Neural Network (DPRNN) with advanced metaheuristic algorithms for automated hyperparameter optimization, with particular emphasis on Greylag Goose Optimization (GGO), alongside other state-of-the-art optimizers. Using historical XAU/USD data spanning from 2004 to February 2025 across multiple temporal resolutions, baseline model evaluation demonstrates that DPRNN outperforms other deep learning architectures prior to optimization, achieving a Mean Squared Error (MSE) of 0.0589, Root Mean Squared Error (RMSE) of 0.2426, and coefficient of determination (R2) of 0.79. Following optimization, the proposed GGO-optimized DPRNN framework yields a substantial performance enhancement, reducing the MSE to 2.05 × 10−5 and RMSE to 4.52 × 10−3, while simultaneously increasing the correlation coefficient to 0.987 and R2 to 0.983, with near-perfect agreement metrics reflected by a Nash–Sutcliffe Efficiency of 0.986 and Willmott Index of 0.988. These results confirm the effectiveness of GGO in navigating complex hyperparameter search spaces and significantly improving predictive accuracy and stability. From an economic and financial perspective, the findings underscore the practical value of metaheuristic-optimized deep learning models for enhancing gold price forecasting, supporting more informed investment decisions, improved risk management, and greater market efficiency in volatile and uncertain financial environments.
Gold price forecasting , Financial time-series modeling , Safe-haven assets , Metaheuristic optimization , Deep learning in financial markets
[1] W. Zhang, Y. Zhan, and Y. Liang, “Financial openness, major events, and exchange rate linkage: Empirical analysis based on the dcc-midas model,” International Review of Financial Analysis, vol. 106, p. 104 578, 2025, ISSN: 1057-5219. DOI: https : / / doi . org / 10 . 1016 / j . irfa . 2025 . 104578. [Online]. Available: https://www.sciencedirect.com/science/article/ pii/S1057521925006659.
[2] I. Özkal, Ë™I. A. Özkan, and F. Ba¸sçiftçi, “Metaverse token price forecasting using artificial neural networks (anns) and adaptive neural fuzzy inference system (anfis),” Neural Computing and Applications, vol. 36, no. 7, pp. 3267–3290, 2024. DOI: https://doi.org/10.1007/s00521- 023-09228-y.
[3] W. Dammak, H. Gökgöz, and A. Jeribi, “Analysis of gold, bitcoin, and gold-backed cryptocurrencies as safe havens during global crises: A focus on artificial intelligence companies,” Computational Economics, vol. 66, no. 4, pp. 2843–2872, 2025. DOI: https://doi.org/10.1007/s10614- 024-10757-4.
[4] J. Moreira, R. Pascoal, and H. Rocha, “Multifractal analysis of gold as a hedge against geopolitical risk,” in Computational Science and Its Applications – ICCSA 2025 Workshops, O. Gervasi et al., Eds., Cham: Springer Nature Switzerland, 2026, pp. 207–224, ISBN: 978-3-031-97596-7.
[5] W. Kristjanpoller and B. M. Tabak, “Comparison of the asymmetric multifractal behavior of green andus bonds against benchmark financial assets,” Financial Innovation, vol. 11, no. 1, p. 57, 2025. DOI: https://doi.org/10.1186/s40854-024-00698-0.
[6] E. Ayadi and N. Ben Mbarek, “The dynamic effects of economic uncertainties and geopolitical risks on saudi stock market returns: Evidence from local projections,” Journal of Risk and Financial Management, vol. 18, no. 5, 2025, ISSN: 1911-8074. DOI: 10 . 3390 / jrfm18050264. [Online]. Available: https://www.mdpi.com/1911-8074/18/5/264.
[7] P. M. Lefatsa, S. Msomi, H. T. Muguto, L. Muguto, and P.-F. Muzindutsi, “An empirical analysis of the impact of global risk sentiment, gold prices, and interest rate differentials on exchange rate dynamics in south africa,” International Journal of Financial Studies, vol. 13, no. 3, 2025, ISSN: 2227-7072. DOI: 10 . 3390 / ijfs13030120. [Online]. Available: https : / / www . mdpi . com / 2227 - 7072/13/3/120.
[8] S. Li and Y. Liu, “A new perspective on gold as a risk hedge: Long-term impacts of bilateral political tensions between the u.s. and china,” International Review of Economics & Finance, vol. 106, p. 104 918, 2026, ISSN: 1059-0560. DOI: https : / / doi . org / 10 . 1016 / j . iref . 2026 . 104918. [Online]. Available: https://www.sciencedirect.com/science/article/ pii/S1059056026000316.
[9] U. A. Sheikh, M. Asad, Z. Ahmed, and U. Mukhtar, “Asymmetrical relationship between oil prices, gold prices, exchange rate, and stock prices during global financial crisis 2008: Evidence from pakistan,” Cogent Economics & Finance, vol. 8, no. 1, D. McMillan, Ed., p. 1 757 802, 2020. DOI: 10.1080 23322039 . 2020 . 1757802. eprint: https : / / doi . org / 10 . 1080 / 23322039 . 2020 . 1757802. [Online]. Available: https://doi.org/10.1080/23322039.2020.1757802.
[10] S. Pandit and X. Luo, “A novel prediction model to evaluate the dynamic interrelationship between gold and crude oil,” International Journal of Data Science and Analytics, vol. 20, no. 2, pp. 1161–1182, 2025. DOI: https://doi.org/10.1007/s41060-024-00519-8.
[11] A. A. Salisu, R. Gupta, S. Karmakar, and S. Das, “Forecasting output growth of advanced economiesover eight centuries: The role of gold market volatility as a proxy of global uncertainty,” Resources Policy, vol. 75, p. 102 527, 2022, ISSN: 0301-4207. DOI: https : / / doi . org / 10 . 1016 / j . resourpol . 2021 . 102527. [Online]. Available: https : / / www . sciencedirect . com / science/article/pii/S0301420721005341.
[12] A. Ampountolas, “Enhancing forecasting accuracy in commodity and financial markets: Insights from garch and svr models,” International Journal of Financial Studies, vol. 12, no. 3, 2024, ISSN: 2227-7072. DOI: 10 . 3390 / ijfs12030059. [Online]. Available: https : / / www . mdpi . com / 2227 - 7072/12/3/59.
[13] F. Wang, J. Chang, W. Zuo, and W. Zhou, “Research on efficiency and multifractality of gold market under major events,” Fractal and Fractional, vol. 8, no. 8, 2024, ISSN: 2504-3110. DOI: 10.3390/ fractalfract8080488. [Online]. Available: https://www.mdpi.com/2504-3110/8/8/ 488.
[14] J. Gao, C. Fan, L. Xu, H. Chen, H. Chen, and Z. Liang, “Intelligent decision making and risk management in stock index futures markets under the influence of global geopolitical volatility,” Omega, vol. 133, p. 103 272, 2025, ISSN: 0305-0483. DOI: https://doi.org/10.1016/j.omega. 2024 . 103272. [Online]. Available: https : / / www . sciencedirect . com / science /article/pii/S0305048324002366.
[15] D. Gabauer, R. Gupta, S. Karmakar, and J. Nielsen, “Stock market bubbles and the forecastability of gold returns and volatility,” Applied Stochastic Models in Business and Industry, 2025. DOI: https//doi.org/10.1002/asmb.2887.
[16] M. Küçük, F. Çebi, and A. T. Tekin, “Xau/usd price prediction using deep learning: Hyperparameter optimization with bayesian, grey-wolf and genetic algorithms,” in Intelligent and Fuzzy Systems,C. Kahraman et al., Eds., Cham: Springer Nature Switzerland, 2025, pp. 96–103, ISBN: 978-3-031-97992-7.
[17] S. Shayganfard, S. S. Moghadam, and M. Salehirad, “Forecasting gold prices (global ounce) using time series models and deep learning,” in 2025 11th International Conference on Web Research (ICWR), 2025, pp. 610–616. DOI: 10.1109/ICWR65219.2025.11006217.
[18] R. Popli, I. Kansal, R. Kumar, V. Khullar, P. Sharma, and D. Parsad, “Gold price prediction in stockexchange using lstm and bi-lstm multivariate deep learning approaches,” in Computational Intelligence and Mathematical Applications, CRC Press, 2024, pp. 1–5.
[19] Shobhit, S. Khan, S. Banerjee, N. Chaudhary, and B. Shukla, “Forecasting gold prices in uzbekistan: An analytical approach to market dynamics and economic indicators using machine learning techniques,” in 2025 International Conference on Technology Enabled Economic Changes (InTech), 2025, pp. 678–682. DOI: 10.1109/InTech64186.2025.11198562.
[20] K. N. TP and S. Sultana, “Advanced techniques for daily gold price forecasting in india through statistical analysis and predictive modeling,” in 2024 8th International Conference on ComputationalSystem and Information Technology for Sustainable Solutions (CSITSS), 2024, pp. 1–6. DOI: 10. 1109/CSITSS64042.2024.10816779.
[21] A. Biju, B. P. Alapatt, and J. P. George, “Ensemble hybrid lstm architectures for robust multi-currency forex forecasting,” in 2025 6th International Conference on Intelligent Communication Technologies and Virtual Mobile Networks (ICICV), 2025, pp. 490–498. DOI: 10.1109/ICICV64824.2025. 11085759.
[22] A. H. Baradaran, M. Bohlouli, and M. R. J. Motlagh, “Decoding tomorrow’s gold prices: A comparative study of gru and cnn-lstm in the iranian market,” in 2024 10th International Conference on Web Research (ICWR), 2024, pp. 329–334. DOI: 10.1109/ICWR61162.2024.10533331.
[23] M. M. Billah and S. Das, “Analysis and prediction of gold price using cnn and bi-gru based neuralnetwork model,” in 2021 24th International Conference on Computer and Information Technology (ICCIT), 2021, pp. 1–6. DOI: 10.1109/ICCIT54785.2021.9689880.
[24] M. F. Sert, “A hybrid arima-lstm/gru model for forecasting monthly trends in turkey’s gold and currency markets with a macro-economic data-driven approach,” in Machine Learning in Finance: Trends, Developments and Business Practices in the Financial Sector, M. Gün and B. Kartal, Eds. Cham:Springer Nature Switzerland, 2025, pp. 35–51, ISBN: 978-3-031-83266-6. DOI: 10 . 1007 / 978 - 3- 031- 83266- 6_3. [Online]. Available: https://doi.org/10.1007/978- 3- 031- 83266-6_3.
[25] B. D. Iswara, P. Sugiartawan, and A. S. Kusuma, “Integration of conformal prediction in automated forex trading systems: Development and evaluation,” in 2025 IEEE International Symposium on Consumer Technology (ISCT), 2025, pp. 389–394. DOI: 10.1109/ISCT66099.2025.11297372.
[26] S. Anbaee Farimani, M. V. Jahan, and A. Milani Fard, “An adaptive multimodal learning model for financial market price prediction,” IEEE Access, vol. 12, pp. 121 846–121 863, 2024. DOI: 10.1109/ ACCESS.2024.3441029.
[27] Y. Wang, M. F. Ghazali, R. Ab Razak, and M. A. S. Zaidi, “Complex system and ps-lstm prediction of cryptocurrencies, stocks, bonds, exchange rates and commodities,” Physica A: Statistical Mechanics and its Applications, vol. 679, p. 130 976, 2025, ISSN: 0378-4371. DOI: https://doi.org/10. 1016/j.physa.2025.130976. [Online]. Available: https://www.sciencedirect.com/ science/article/pii/S0378437125006284.
[28] E. Njoki, J. S. Wekesa, and D. G. Njagi, “Ensemble learning for foreign exchange market trendprediction,” Computational Economics, pp. 1–16, 2025. DOI: https : / / doi . org / 10 . 1007 / s10614-025-11102-z.
[29] Z. A. Hassaan, M. H. Yacoub, and L. A. Said, “Fpga-accelerated esn with chaos training for financial time series prediction,” Machine Learning and Knowledge Extraction, vol. 7, no. 4, 2025, ISSN: 2504-4990. DOI: 10.3390/make7040160. [Online]. Available: https://www.mdpi.com/ 2504-4990/7/4/160.
[30] P. Srichaiyan, K. Y. Tippayawong, and A. Boonprasope, “Forecasting soybean futures prices with adaptive ai models,” IEEE Access, vol. 13, pp. 48 239–48 256, 2025. DOI: 10.1109/ACCESS.2025. 3546786.
