Article Details

Abstract

Gold prices are influenced by multiple factors such as macroeconomic conditions, geopolitical events, and market sentiment, exhibiting high complexity and posing significant challenges for accurate forecasting. Reliable prediction is crucial for financial asset allocation and risk management. To address this, this study proposes a multivariate-driven gold price forecasting framework and constructs a hybrid quantum-classical neural network model. The model deeply integrates parameterized quantum circuits with LSTM networks, leveraging the parallel processing capabilities of quantum computing to enhance the capture of nonlinear dynamic features. Based on an empirical analysis of gold price data from 2022 to 2025, the results demonstrate that the model converges faster and requires approximately 30 times fewer parameters than classical algorithms. It outperforms the LSTM model across evaluation metrics such as MAE, RMSE, and R². This study confirms the strong expressive power and high robustness of the proposed model, highlighting its potential to improve the performance of financial time series forecasting and offering a new technical pathway for gold market analysis and quantitative decision-making.

Keywords

gold price prediction; quantum finance; hybrid quantum-classical neural network; deep learning

References

1. [1] Nanhiya D，Gopal S B，Balakumar S，et al. Gold Price Prediction Using ARIMA Model [C]//Proceedings of the ViTECON 2023-2nd IEEE International Conference on Vision Towards Emerging Trends in Communication and Networking Technologies，2023：1-6.
2. [2] Yang J，De Montigny D，Treleaven P. ANN, LSTM, and SVR for Gold Price Forecasting [C]//2022 IEEE Symposium on Computational Intelligence for Financial Engineering and Economics (CIFEr)，2022：1-7.
3. [3] Ben Jabeur S，Mefteh-Wali S，Viviani J L. Forecasting Gold Price With the XGBoost Algorithm and SHAP Interaction Values [J].Annals of Operations Research，2024，334：679-699.
4. [4] Zhang X，Zhang L，Zhou Q，et al. A Novel Bitcoin and Gold Prices Prediction Method Using an LSTM-P Neural Network Model [J/OL].Computational Intelligence and Neuroscience，2022：1643413（2022-05-05）.https://doi.org/10.1155/2022/1643413.
5. [5] Jiang Yuyan, Huang Tichen, Gan Rumei Jiang, etc Research on Gold Futures Price Prediction Based on KANsLTformer [J]. China Management Science, 2026, 34 (5): 11-20
6. [6] Luan Tian, Kuang Xueheng, Gao Yansong, etc Exploration of the Application of Quantum Computing Technology in the Financial Field [J]. Computer Application Research, 2024 (7): 1921-1929
7. [7] Wang Jian, Zhang Rui, Jiang Nan A Review of Quantum Machine Learning [J]. Journal of Software, 2024 (8): 3843-3877
8. [8] Zhang Xiaoxu, Gao Zhentao, Wu Lei, etc Stock price prediction based on hybrid quantum classical neural network model [J]. Journal of University of Electronic Science and Technology of China, 2022 (1): 16-23
9. [9] Sun Jingyun, Wei Chen Research on Gold Futures Price Prediction Based on Text Sentiment Analysis and LightGBM-LSTM Model [J]. Journal of Nanjing University of Information Science and Technology, 2025 (5): 679-691
10. [10] Yang Chen, Chen Guici International Gold Futures Price Prediction Based on EMD-LSTM [J]. Journal of Central South University for Nationalities (Natural Science Edition), 2023 (6): 857-864
11. [11] Saini A，Singh K R，Sinha P. Forecasting Gold Price Using Hybrid Deep Neural Network LSTM-Autoencoder [J/OL].Discover Artificial Intelligence，2025，5（1）：281.https://doi.org/10.1007/s44163-025-00464-w.
12. [12] Bao G，Niu Y，Cui B，et al. Revealing the Correlation Between Economic Indicators and Gold Prices for Forecasting：Medium Term Forecast Framework With Data Patch [J/OL].Expert Systems With Applications，2026，298：129594.https://doi.org/10.1016/j.eswa.2025.129594.
13. [13] Charugulla S，Saheb S S. Gold Futures Price Prediction Using Transformer Deep Learning Models With Data Scraped via UiPath [J/OL].Journal of Visualized Experiments，2025（223）：e66123.https://dx.doi.org/10.3791/68903.
14. [14] Li X Q，Ma X Q. Jumps and Gold Futures Volatility Prediction [J/OL].Finance Research Letters，2023，58：104492（2023-09-23）.https://doi.org/10.1016/j.frl.2023.104492.
15. [15] Guo Yangli, Ma Feng Research on Volatility Prediction of Gold Futures Market Based on Markov and Mixed Frequency Data Model [J]. China Management Science, 2024 (1): 13-22
16. [16] Livieris I E，Pintelas E，Pintelas P. A CNN-LSTM Model for Gold Price Time-Series Forecasting [J].Neural Computing and Applications，2020，32：17351-17360.
17. [17] Angelova T G，Raychev S，Ilieva G. A Framework for Gold Price Prediction Combining Classical and Intelligent Methods With Financial，Economic，and Sentiment Data Fusion [J/OL].International Journal of Financial Studies，2025，13（2）：102. https://doi.org/10.3390/ijfs13020102.
18. [18] Liu Z M，Wang Y X，Vaidya S，et al. KAN：Kolmogorov-Arnold Networks [PP/OL].（2025-02-09）.https://arxiv.org/abs/2404.19756.
19. [19] Zhou Ruiming, Zhang Yanhui Application of stationary time series analysis in gold price prediction [J]. China Securities and Futures, 2025 (5): 36-41
20. [20] He Yiyue, Chen Qianqian, Gao Ni, etc Research on Integrated Prediction of Gold Futures Prices Based on MEMD-WGAN-GP [J]. Systems Engineering Theory and Practice, 2025, 45 (6): 2033-2049
21. [21] Zhao Y，Guo Y，Wang X. Hybrid LSTM–Transformer Architecture With Multi-Scale Feature Fusion for High-Accuracy Gold Futures Price Forecasting [J].Mathematics，2025，13（10）：1551.https://doi.org/10.3390/math13101551.

About the authors

Zhao Xiumin (2003-), female, Han ethnicity, from Baoding, Hebei Province, is currently pursuing a master's degree in quantum finance; Corresponding author: Wang Wei (1984-), male, Han nationality, from Baoding, Hebei Province, associate professor, doctoral student, research direction: intelligent control, intelligent risk control, optimal control.