Attention-Enhanced LSTM Deep Learning Network for Gold ‎Futures Forecasting

  • Authors

    • Sa’eed Serwan Abdulsattar Dept of Electrical and Electronics Engineering, University of Bahrain
    • Hani Al-Balasmeh Dept of Informatics Engineering, College of Engineering, University of Technology, Bahrain https://orcid.org/0000-0003-3643-0769
    • Rahmeh Abdulkaeem Jaber Department of Computer Studies, University of Technology, Bahrain
    • Fayzeh Abdulkareem Jaber Dept Business Administration, University of Technology, Bahrain
    https://doi.org/10.14419/kexs8879

    Received date: October 11, 2025

    Accepted date: October 29, 2025

    Published date: November 5, 2025

  • Gold Futures; Deep Learning; LSTM; Attention Mechanism; Time Series Forecasting

  • Abstract

    This study presents an advanced deep learning framework for forecasting gold futures prices by integrating a dual-attention Long Short-Term Memory (LSTM) network with a comprehensive set of engineered technical indicators. The proposed model employs temporal attention to dynamically reweight historical time steps and feature-level attention to adaptively prioritize influential indicators such as momentum, ‎volatility, and trend measures. This dual mechanism enables the network to capture nonlinear dependencies and shifting market regimes ‎more effectively than conventional models.‎

    Empirical evaluation using COMEX Gold Futures (Ticker: GC1) data obtained from Investing.com, covering the period January 2010 to ‎May 2025, demonstrates the model’s superior forecasting accuracy. The proposed framework achieves a Mean Absolute Percentage Error ‎‎(MAPE) of 0.91% and a coefficient of determination (R²) of 0.995 after calibration, representing a 34.7% reduction in MAE compared with ‎the baseline LSTM. The lag-aware calibration module further refines short-term directional forecasts. At the same time, the dual-attention ‎layers enhance interpretability by revealing the relative importance of indicators and time intervals across market conditions.‎

    By combining sequential modeling, adaptive feature selection, and explainable attention visualization, this research delivers a transparent, ‎scalable, and high-performance forecasting framework. The findings offer practical value for traders, analysts, and policymakers seeking ‎reliable and interpretable tools to navigate uncertainty and volatility in commodity markets‎.

  • References

    1. D. G. Baur and B. M. Lucey, “Is Gold a Hedge or a Safe Haven? An Analysis of Stocks, Bonds and Gold,” Financial Review, vol. 45, no. 2, pp. 217–229, May 2010, https://doi.org/10.1111/j.1540-6288.2010.00244.x.
    2. P. Foroutan and S. Lahmiri, “Deep learning systems for forecasting the prices of crude oil and precious metals,” Financial Innovation, vol. 10, Art. no. 111, Jul. 2024. https://doi.org/10.1186/s40854-024-00637-z.
    3. L. Rubio, A. P. Pinedo, A. M. Castano, and F. Ramos, “Forecasting˜ volatility by using wavelet transform, ARIMA and GARCH models,” Eura-sian Economic Review, vol. 13, no. 4, pp. 803–830, Dec. 2023, https://doi.org/10.1007/s40822-023-00243-x.
    4. D. N. Dhanush, R. Ramesh, P. R. Prajapati, A. Kodipalli, M. Revanth, and R. J. Martis, “Prediction of Gold Price using Deep Learning,” in 2021 IEEE 9th Region 10 Humanitarian Technology Conference (R10HTC), 2021, pp. 1–6, https://doi.org/10.1109/R10-HTC53172.2021.9641719.
    5. S. Hochreiter and J. Schmidhuber, “Long Short-Term Memory,” Neural Computation, vol. 9, no. 8, pp. 1735–1780, Nov. 1997. 1735–1780, Nov. 1997, https://doi.org/10.1162/neco.1997.9.8.1735.
    6. H. Ke and Z. Zuominyang, “Predicting Chinese Commodity Futures Price: An EEMD-Hurst-LSTM Hybrid Approach,” IEEE Access, vol. 11, pp. 1–1, Jan. 2023, https://doi.org/10.1109/ACCESS.2023.3239924.
    7. R. J. Shiller, “From Efficient Markets Theory to Behavioral Finance,” Journal of Economic Perspectives, vol. 17, no. 1, pp. 83–104, Winter 2003. https://doi.org/10.1257/089533003321164967.
    8. C. Zhang, N. N. A. Sjarif, and R. Ibrahim, “Deep learning models for price forecasting of financial time series: A review of recent advancements: 2020–2022,” WIREs Data Mining and Knowledge Discovery, vol. 14, Art. no. e1519, 2024, https://doi.org/10.1002/widm.1519.
    9. M. Wu and X. Diao, “Technical analysis of three stock oscillators testing MACD, RSI, and KDJ rules in SH & SZ stock markets,” in 2015 4th In-ternational Conference on Computer Science and Network Technology (ICCSNT), Harbin, China, 2015, pp. 320–323, https://doi.org/10.1109/ICCSNT.2015.7490760.
    10. K. Masuda, H. Kimura, and S. Ghosh, “Deep learning for oil and commodity price prediction: An empirical study using multivariate
    11. LSTM,” Resources Policy, vol. 76, Art. no. 102555, 2022, https://doi.org/10.1016/j.resourpol.2022.102555.
    12. F. Shahid, M. Zameer, and A. Muneeb, “Predicting Stock Market Trends Using Machine Learning: A Comparative Study of LSTM and ARIMA Models,” Financial Innovation, vol. 7, no. 28, 2021.
    13. D. Bahdanau, K. Cho, and Y. Bengio, “Neural Machine Translation by Jointly Learning to Align and Translate,” in Proc. 3rd Int. Conf. Learn. Rep-resentations (ICLR), 2015.
    14. Y. Qin, D. Song, H. Chen, W. Cheng, G. Jiang, and G. Cottrell, “A Dual-Stage Attention-Based Recurrent Neural Network for Time Series Predic-tion,” arXiv preprint arXiv:1704.02971, 2017. https://doi.org/10.24963/ijcai.2017/366.
    15. S. B. S., N. S. Fatima, and M. Abbas, “Enhancing Stock Market Prediction with an LSTM-Attention Model Integrating Macroeconomic and Sen-timent Features,” in 2024 Int. Conf. on Innovative Computing, Intelligent Communication and Smart Electrical Systems (ICSES), Chennai, India, 2024, pp. 1–6, https://doi.org/10.1109/ICSES63760.2024.10910478.
    16. S.-J. Bu and S.-B. Cho, “Time series forecasting with multi-headed attention-based deep learning for residential energy consumption,” Energies, vol. 13, no. 18, Art. no. 4722, Sep. 2020, https://doi.org/10.3390/en13184722.
    17. R. Govindaraj, A. Thakur, and V. Rajagopalan, “Interpretable financial forecasting using SHAP and attention-based LSTM networks,” Journal of Computational Finance, vol. 25, no. 3, pp. 45–62, 2023.
    18. Y. Liu, C. Zhang, and H. Li, “Attention heatmaps for explainable stock price prediction: A transformer-based approach,” Applied Soft Computing, vol. 118, Art. no. 108456, 2022.
    19. Investing.com, Gold Futures Historical Data (Ticker: GC1, COMEX), available: https://www.investing.com/commodities/gold-historical-data, ac-cessed: May 23, 2025.

  • Downloads

  • How to Cite

    Abdulsattar , S. S. ., Al-Balasmeh, H., Jaber, R. A. ., & Jaber, F. A. . (2025). Attention-Enhanced LSTM Deep Learning Network for Gold ‎Futures Forecasting. International Journal of Basic and Applied Sciences, 14(7), 166-174. https://doi.org/10.14419/kexs8879