隨著全球環境日趨複雜多變，黃金現貨價格呈現出高度的非線性與波動聚集特徵。傳統經濟計量模型受限於全域常數線性假設，難以有效捕捉基本面特徵在面臨極端衝擊時的非線性變化。鑑於此，本研究系統性整合黃金自身歷史價格（OHLC 基線特徵）、總體經濟指標（實質利率、通膨、美元指數等）與不確定性因子（VIX、EPU、GPR），建構單一時序（LSTM、BiLSTM）與空間、時序深度學習混合模型架構，並導入可解釋人工智慧（XAI）之 SHAP 演算法，旨在提升模型之可解釋性，深入探討核心定價特徵之動態非線性特徵交互調控行為。
本研究將實證樣本依據市場狀態劃分為平穩期（2017–2019）、疫情衝擊期（2020）、升息緊縮期（2022）與降息寬鬆期（2025）四個異質市場狀態進行樣本外點預測績效評估。本研究放寬傳統假設，集中提煉出三大核心學術貢獻：
一、展現黃金資產之市場狀態相依架構（Market State Dependent Framework），實證結果顯示外部基本面成本與不確定性因子之資訊貢獻程度，在不同市場狀態下呈現差異，其重要性與排名隨市場狀態轉換而展現異質波動特徵。
二、揭示核心機會成本與情緒、風險要素之非線性交互作用，透過可解釋人工智慧SHAP二階狀態相依圖顯示，實質利率並未在危機或政策轉折期「消失」，而是其對模型之邊際預測貢獻隨市場狀態產生非線性動態調控。在承平時期，實質利率於模型中展現相對顯著之負向邊際預測貢獻；然而當外生不確定性因子（VIX、EPU、GPR）處於極端高位時，避險需求引發高維非線性交互作用，使模型對利率的邊際相依路徑產生變化。
三、支持深度學習在高效資產環境中的特徵萃取學理價值，實證複雜模型在日頻預測上未能穩定超越傳統 ARIMAX 與隨機漫步模型，結果顯示深度學習模型於日頻價格預測上的優勢有限，其應用價值可能更偏向於非線性特徵辨識與資訊萃取。本研究提煉出資產定價之市場狀態相依理論意涵，明確展現動態決策之核心學術價值。

Spot gold prices exhibit strong non-linear and volatility clustering characteristics un-der complex global environments. Traditional econometric models, constrained by linear assumptions, struggle to capture fundamental dynamics under extreme shocks. This study integrates daily OHLC baseline features, macroeconomic indicators, and uncertainty factors into sequential and spatial-temporal deep learning frameworks, applying SHAP-based Explainable AI across four distinct regimes: stable (2017–2019), pandemic shock (2020), monetary tightening (2022), and monetary easing (2025).
This thesis delivers three primary academic contributions:
First, it establishes a market state dependent framework, demonstrating that the mar-ginal information contributions and importance rankings of exogenous features vary significantly across regimes.
Second, it reveals the non-linear interaction between fundamental opportunity costs and risk dimensions. Crucially, the Real Interest Rate has not "disappeared"; rather, its marginal predictive contribution dynamically shifts across market states. While real interest rates maintain a negative marginal contribution during calm periods, extreme tail-risk shocks reconfigure the network's feature reliance.
Third, it confirms that deep learning models do not consistently outperform linear ARIMAX and Random Walk benchmarks on a daily point forecasting frequency. These findings provide empirical evidence consistent with weak-form market efficiency, validating neural networks as robust non-linear feature extractors rather than point forecasters. Overall, this research conceptualizes asset valuation within dynamic macro-regimes.

Ahmad, M., Khan, S., Ahmad, R. W., & Rehman, A. A. (2025). Comparative analysis of statistical and machine learning models for gold price prediction. Journal of Media Horizons, 6(4), 50–65.
Aizenman, J., & Inoue, K. (2013). Central banks and gold puzzles. Journal of the Japanese and International Economies, 28, 69–90.
Amini, A., & Kalantari, R. (2024). Gold price prediction by a CNN-Bi-LSTM model along with automatic parameter tuning. PLoS One, 19(3), e0298426. https://doi.org/10.1371/journal.pone.0298426
Anh, N. B., & Zhao, Y. Q. (2021). Half Century of Gold Price: Regime-Switching and Forecasting Framework. International Journal of Financial Research, 12(3). https://doi.org/10.5430/ijfr.v12n3p1
Barsky, R. B., & Summers, L. H. (1988). Gibson's paradox and the gold standard. Journal of Political Economy, 96(3), 528–550.
Baur, D. G., & McDermott, T. K. (2010). Is gold a safe haven? International evidence. Journal of Banking & Finance, 34(8), 1886–1898. https://doi.org/10.1016/j.jbankfin.2009.12.008
Beckmann, J., Berger, T., & Czudaj, R. (2015). Does gold act as a hedge or a safe haven for stocks? A smooth transition approach. Economic Modelling, 48, 16–24.
Beckmann, J., & Czudaj, R. (2013). Oil and gold price dynamics in a multivariate cointegration framework. International Economics and Economic Policy, 10(3), 453–468. https://doi.org/10.1007/s10368-013-0237-8
Ben Ameur, H., Jamaani, F., & M, N. A. A. (2024). Examining the safe-haven and hedge capabilities of gold and cryptocurrencies: A GARCH and regression quantiles approach in geopolitical and market extremes. Heliyon, 10(22), e40400. https://doi.org/10.1016/j.heliyon.2024.e40400
Bildirici, M. E., Salman, M., & Ersin, Ö. Ö. (2022). Nonlinear contagion and causality nexus between oil, gold, VIX investor sentiment, exchange rate and stock market returns: The MS-GARCH copula causality method. Mathematics, 10(21), 4035.
Bilgin, M. H., Gozgor, G., Lau, C. K. M., & Sheng, X. (2018). The effects of uncertainty measures on the price of gold. International Review of Financial Analysis, 58, 1–7.
Blose, L. E. (2010). Gold prices, cost of carry, and expected inflation. Journal of Economics and Business, 62(1), 35–47. https://doi.org/10.1016/j.jeconbus.2009.07.001
Caldara, D., & Iacoviello, M. (2018). Measuring Geopolitical Risk. International Finance Discussion Papers, 2018.0(1222), 1–66. https://doi.org/10.17016/ifdp.2018.1222
Capie, F., Mills, T. C., & Wood, G. (2005). Gold as a hedge against the dollar. Journal of International Financial Markets, Institutions and Money, 15(4), 343–352. https://doi.org/10.1016/j.intfin.2004.07.002
Caporale, G. M., & Gil-Alana, L. A. (2023). Gold and silver as safe havens: A fractional integration and cointegration analysis. PLoS One, 18(3), e0282631.
Chahed, K., Sadraoui, T., & Azouzi, M. A. (2025). The Impact of Geopolitical Risks on Gold Prices: Empirical Evidence from the Israeli-Palestinian Conflict. Journal of Posthumanism, 5(10), 421–445. https://doi.org/10.63332/joph.v5i10.3559
Chew, L. M., Yi, S. N. C., & Yeng, O. L. (2023). Gold Prices Forecasting Using Bidirectional LSTM Model Based on SPX500 Index, USD Index, Crude Oil Prices and CPI. 2023 11th International Conference on Information and Communication Technology (ICoICT),
Christie–David, R., Chaudhry, M., & Koch, T. W. (2000). Do macroeconomics news releases affect gold and silver prices? Journal of Economics and Business, 52(5), 405–421.
Cohen, G., & Qadan, M. (2010). Is gold still a shelter to fear? American Journal of Social and Management Sciences, 1(1), 39–43. https://doi.org/10.5251/ajsms.2010.1.1.39.43
Demajo, N. (2025). An analysis of the relationship between real yields and gold prices: a pre and post Covid analysis University of Malta].
Erb, C. B., & Harvey, C. R. (2013). The golden dilemma. Financial Analysts Journal, 69(4), 10–42.
Ghosh, D., Levin, E. J., Macmillan, P., & Wright, R. E. (2004). Gold as an inflation hedge? Studies in Economics and Finance, 22(1), 1–25.
Gujarati, D. N. (2012). Basic Econometrics 4th ed. In.
Hair Jr, J. F., Black, W. C., Babin, B. J., & Anderson, R. E. (2010). Multivariate data analysis. In Multivariate data analysis (pp. 785–785).
He, Q., Guo, Y., & Yu, J. (2020). Nonlinear dynamics of gold and the dollar. The North American Journal of Economics and Finance, 52. https://doi.org/10.1016/j.najef.2020.101160
He, Z., O'Connor, F., & Thijssen, J. (2018). Is gold a Sometime Safe Haven or an Always Hedge for equity investors? A Markov-Switching CAPM approach for US and UK stock indices. International Review of Financial Analysis, 60, 30–37.
He, Z., Zhou, J., Dai, H.-N., & Wang, H. (2019). Gold price forecast based on LSTM-CNN model. 2019 IEEE Intl Conf on Dependable, Autonomic and Secure Computing, Intl Conf on Pervasive Intelligence and Computing, Intl Conf on Cloud and Big Data Computing, Intl Conf on Cyber Science and Technology Congress (DASC/PiCom/CBDCom/CyberSciTech),
Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural computation, 9(8), 1735–1780.
Hood, M., & Malik, F. (2013). Is gold the best hedge and a safe haven under changing stock market volatility? Review of Financial Economics, 22(2), 47–52. https://doi.org/10.1016/j.rfe.2013.03.001
Jia, Y., Dong, Z., An, H., & Srinivasan, K. (2023). Study of the Modal Evolution of the Causal Relationship between Crude Oil, Gold, and Dollar Price Series. International Journal of Energy Research, 2023, 1–15. https://doi.org/10.1155/2023/7947434
Jones, A. T., & Sackley, W. H. (2016). An uncertain suggestion for gold-pricing models: the effect of economic policy uncertainty on gold prices. Journal of Economics and Finance, 40(2), 367–379.
Jubinski, D., & Lipton, A. F. (2013). VIX, gold, silver, and oil: how do commodities react to financial market volatility? Journal of Accounting and Finance, 13(1), 70–88.
Le, T.-H., & Chang, Y. (2011). Oil and gold: correlation or causation?
LeCun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998). Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11), 2278–2324.
Levin, E. J., Montagnoli, A., & Wright, R. (2006). Short-run and long-run determinants of the price of gold.
Li, J. (2024). Gold price prediction based on CNN-LSTM. Financial Engineering and Risk Management, 7(2).
Livieris, I. E., Pintelas, E., & Pintelas, P. (2020). A CNN–LSTM model for gold price time-series forecasting. Neural Computing and Applications, 32(23), 17351–17360. https://doi.org/10.1007/s00521-020-04867-x
Lucey, B. M., Sharma, S. S., & Vigne, S. A. (2017). Gold and inflation (s)–A time-varying relationship. Economic Modelling, 67, 88–101.
Madhika, Y. R., Kusrini, K., & Hidayat, T. (2023). Gold price prediction using the ARIMA and LSTM models. Sinkron: jurnal dan penelitian teknik informatika, 7(3), 1255–1264.
Mohtasham Khani, M., Vahidnia, S., & Abbasi, A. (2021). A Deep Learning-Based Method for Forecasting Gold Price with Respect to Pandemics. SN Comput Sci, 2(4), 335. https://doi.org/10.1007/s42979-021-00724-3
Pierdzioch, C., Risse, M., & Rohloff, S. (2014). On the efficiency of the gold market: Results of a real-time forecasting approach. International Review of Financial Analysis, 32, 95–108.
Qin, M., Su, C.-W., Xiao, Y.-D., & Zhang, S. (2020). Should Gold Be Held under Global Economic Policy Uncertainty? Journal of Business Economics and Management, 21(3), 725–742. https://doi.org/10.3846/jbem.2020.12040
Rahmadani, D. (2025). The role of gold as a safe haven asset in risk management strategies in the era of geopolitical and monetary uncertainty. Available at SSRN 5338848.
Reboredo, J. C. (2013). Is gold a safe haven or a hedge for the US dollar? Implications for risk management. Journal of Banking & Finance, 37(8), 2665–2676. https://doi.org/10.1016/j.jbankfin.2013.03.020
Sharma, S. S. (2016). Can consumer price index predict gold price returns? Economic Modelling, 55, 269–278. https://doi.org/10.1016/j.econmod.2016.02.014
Shen, L., Shen, K., Yi, C., & Chen, Y. (2020). Regression and Hidden Markov Models for Gold Price Prediction. 2020 IEEE International Conference on Big Data (Big Data),
Sjaastad, L. A., & Scacciavillani, F. (1996). The price of gold and the exchange rate. Journal of international Money and Finance, 15(6), 879–897.
Smales, L. A. (2014). News sentiment in the gold futures market. Journal of Banking & Finance, 49, 275–286.
Synek, R. (2024). Cointegration analysis of US M2 and gold price over the last half century. European Financial and Accounting Journal, 19(1), 1–19.
Taghipour, H., Rezaee, A., & Hajati, F. (2025). Gold Price Prediction Using Long Short-Term Memory and Multi-Layer Perceptron with Gray Wolf Optimizer. arXiv preprint arXiv:2512.22606.
Taneva-Angelova, G., & Ilieva, G. (2026). Forecasting gold prices: a comparative analysis of traditional and deep learning methods The interdisciplinary approach in economic and social sciences,
Tkacz, G. (2007). Gold prices and inflation.
Triki, M. B., Mohamed, E. S. S., Ahmed, S. I., & Jaghoubi, S. (2026). The impact of geopolitical risk, economic policy uncertainty, and bitcoin on precious metals: Evidence from a dynamic simulated ARDL approach. Edelweiss Applied Science and Technology, 10(2), 824–835. https://doi.org/10.55214/2576-8484.v10i2.12249
Tripurana, N., Kar, B., Chakravarty, S., Paikaray, B., & Satpathy, S. (2022). Gold Price Prediction using Machine Learning Techniques. ACI@ ISIC,
Vidal, A., & Kristjanpoller, W. (2020). Gold volatility prediction using a CNN-LSTM approach. Expert Systems with Applications, 157. https://doi.org/10.1016/j.eswa.2020.113481
Wahyudin, I., Mukhlash, I., Simarmata, D. T., & Iriawan, N. (2025). Comparative Analysis of Time Series and Deep Learning Models for Forecasting Gold Price Under Macroeconomic Conditions 2025 9th International Conference on Information Technology, Information Systems and Electrical Engineering (ICITISEE),
You, W., Chen, J., Xie, H., & Ren, Y. (2025). Which uncertainty measure better predicts gold prices? New evidence from a CNN-LSTM approach. The North American Journal of Economics and Finance, 76. https://doi.org/10.1016/j.najef.2025.102375
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.
Zhang, H., Demirer, R., Huang, J., Huang, W., & Suleman, M. T. (2021). Economic policy uncertainty and gold return dynamics: evidence from high-frequency data. Resources Policy, 72, 102078.
Zhang, Y.-J., & Wei, Y.-M. (2010). The crude oil market and the gold market: Evidence for cointegration, causality and price discovery. Resources Policy, 35(3), 168–177. https://doi.org/10.1016/j.resourpol.2010.05.003
Zhang, Y., Shi, M., & Liu, R. (2025). Will gold prices continue to rise? A time-varying analysis of the dollar-gold nexus under geopolitical and economic uncertainty. Proceedings of Business and Economic Studies, 8(3), 259–275.
翁三能. (2024). 地緣政治風險對國際黃金價格風險的實證分析 國立高雄科技大學國際企業系].