Improving the Accuracy of Precious Metal Prices Forecasts When Used as Stabilization Assets

Precious metals are key elements of the asset class in the international financial market. They have a number of advantages: they are a valuable tool for preserving wealth, they are not at risk of default, and they provide effective protection against inflation. In addition, they are considered safe-haven assets during periods of unfavorable geopolitical conditions. The purpose of this research is to find methods for improving the accuracy of predicting the price of precious metals through the use of advanced machine learning models. The methodological basis is the concept of predicting the effectiveness of precious metals as a stabilizing asset (and a safe-haven asset) in the context of future financial instability. The research methodology is based on evaluating the effectiveness of machine learning models using information criteria such as AIC and BIC, determination coefficients R2 and Adj-R2, and RMSE and MAPE as measures of the closeness between the actual and predicted values of time series and error measures. The information base for this study was based on daily data on the prices of four precious metals (gold, silver, platinum, and palladium), provided by Investing.com. Given the increasing importance of precious metals as indicators of investor sentiment and the state of the global economy, and in light of the escalating geopolitical tensions from 2020 to 2025, we conducted a comparative analysis using modern machine learning models. The results obtained demonstrate the advantages of the KAN model as a promising tool for improving the accuracy of forecasts and the interpretability of results in various scenarios. This is highly significant for the development of an effective investment strategy in the precious metal markets.

1. Baur D. G., Lucey B. M. Is gold a hedge or a safe haven? An analysis of stocks, bonds and gold. The Financial Review. 2010;45(2):217-229. DOI: 10.1111/j.1540-6288.2010.00244.x

2. Reboredo J. C., Rivera-Castro M. A. Can gold hedge and preserve value when the US dollar depreciates? Economic Modelling. 2014;39:168-173. DOI: 10.1016/j.econmod.2014.02.038

3. Su C.-W., Wang K.-H., Lobonţ O.-R., Qin M. Continuous wavelet transform of time-frequency analysis technique to capture the dynamic hedging ability of precious metals. Mathematics. 2023;11(5):1186. DOI: 10.3390/math11051186

4. Mehrdoust F., Noorani M. Forecasting precious metals price based on artificial neural network trained by Lévy flight optimization algorithm. SSRN Electronic Journal. 2024. DOI: 10.2139/ssrn.4722754

5. Eremin V. V. Security of the money supply with gold and foreign exchange reserves as a leading indicator of the ruble exchange rate. Finance: Theory and Practice. 2023;27(3):43-55. DOI: 10.26794/2587-5671-2023-27-3-43-55

6. Karaev A. K. Cryptocurrency price prediction using machine learning technologies: LSTM vs KAN. Vestnik Altaiskoi akademii ekonomiki i prava = Journal of Altai Academy of Economics and Law. 2025;(7-2):261-266. (In Russ.). DOI: 10.17513/vaael.4251

7. Vigne S. A., Lucey B. M., O’Connor F.A., Yarovaya L. The financial economics of white precious metals — a survey. International Review of Financial Analysis. 2017;52:292-308. DOI: 10.1016/j.irfa.2017.04.006

8. Miao M., Khaskheli A., Raza S. A., Yousufi S. Q. Using Internet search keyword data for predictability of precious metals prices: Evidence from non-parametric causality-in-quantiles approach. Resources Policy. 2022;75:102478. DOI: 10.1016/J.RESOURPOL.2021.102478

9. Sikiru A. A., Salisu A. A. Hedging with financial innovations in the Asia-Pacific markets during the COVID‑19 pandemic: The role of precious metals. Quantitative Finance and Economics. 2021;5(2):352-372. DOI: 10.3934/qfe.2021016372

10. Bekaert G., Hoerova M. What do asset prices have to say about risk appetite and uncertainty? Journal of Banking & Finance. 2016;67:103-118. DOI: 10.1016/j.jbankfin.2015.06.015

11. Gulen H., Ion M. Policy uncertainty and corporate investment. The Review of Financial Studies. 2016;29(3):523-564. DOI: 10.1093/rfs/hhv050

12. Duc Huynh T. L., Burggraf T., Nasir M. A. Financialisation of natural resources & instability caused by risk transfer in commodity markets. Resources Policy. 2020;66:101620. DOI: 10.1016/j.resourpol.2020.101620

13. Thongkairat S., Yamaka W., Sriboonchitta S. Economic policy uncertainty effect on precious metal markets: A Markov-switching model with mixture distribution regimes. Thai Journal of Mathematics. 2019:77-92. URL: http://thaijmath.in.cmu.ac.th/index.php/thaijmath/article/view/3907

14. Adekoya O. B., Oliyide J. A., Oduyemi G. O. How COVID‑19 upturns the hedging potentials of gold against oil and stock markets risks: Nonlinear evidences through threshold regression and Markov-regime switching models. Resources Policy. 2021;70:101926. DOI: 10.1016/j.resourpol.2020.101926

15. Van Hoang T. H., Lahiani A., Heller D. Is gold a hedge against inflation? New evidence from a nonlinear ARDL approach. Economic Modelling. 2016;54:54-66. DOI: 10.1016/j.econmod.2015.12.013

16. Lau M. C.K., Vigne S. A., Wang S., Yarovaya L. Return spillovers between white precious metal ETFs: The role of oil, gold, and global equity. International Review of Financial Analysis. 2017;52:316-332. DOI: 10.1016/j.irfa.2017.04.001

17. Ponkratov V. V. The price of oil. Reaching for the bottom. Mir novoi ekonomiki = The World of New Economy. 2016;(1):32-37. (In Russ.).

18. Mingming T., Jinliang Z. A multiple adaptive wavelet recurrent neural network model to analyze crude oil prices. Journal of Economics and Business. 2012;64(4):275-286. DOI: 10.1016/j.jeconbus.2012.03.002

19. Al-Dhuraibi W. A., Ali J. Using classification techniques to predict gold price movement. In: 2018 4th Int. conf. on computer and technology applications (ICCTA). (Istanbul, May 03–05, 2018). New York, NY: IEEE; 2018:127-130. DOI: 10.1109/CATA.2018.8398669

20. E J., Ye J., Jin H. A novel hybrid model on the prediction of time series and its application for the gold price analysis and forecasting. Physica A: Statistical Mechanics and its Applications. 2019;527:121454. DOI: 10.1016/j.physa.2019.121454

21. Guha G. Bandyopadhyay B. Gold price forecasting using ARIMA model. Journal of Advanced Management Science. 2016;4(2):117-121. DOI: 10.12720/joams.4.2.117-121

22. Cohen G. Algorithmic strategies for precious metals price forecasting. Mathematics. 2022;10(7):1134. DOI: 10.3390/math10071134

23. Weng F., Chen Y., Wang Z., et al. Gold price forecasting research based on an improved online extreme learning machine algorithm. Journal of Ambient Intelligence and Humanized Computing. 2020;11(6):4101-4111. DOI: 10.1007/s12652-020-01682-z

24. Duc Huynh T. L., Burggraf T., Wang M. Gold, platinum, and expected Bitcoin returns. Journal of Multinational Financial Management. 2020;56:100628. DOI: 10.1016/j.mulfin.2020.100628

25. Aldeki R. G. Predicting financial market volatility with modern model and traditional model. Finance: Theory and Practice. 2025;29(2):154-165. DOI: 10.26794/2587-5671-2025-29-2-154-165

26. Aravind M. Abnormal return of NSE traded gold ETFS in crisis settings: An appraisal of contrarian versus momentum strategies. Finance: Theory and Practice. 2024;28(6):69-79. DOI: 10.26794/2587-5671-2024-28-6-69-79

27. Varshini A., Kayal P., Maiti M. How good are different machine and deep learning models in forecasting the future price of metals? Full sample versus sub-sample. Resources Policy. 2024;92:105040. DOI: 10.1016/j.resourpol.2024.105040

28. Liu T., Zheng Z. Negotiation assistant bot of pricing prediction based on machine learning. International Journal of Intelligence Science. 2020;10(2):9-21. DOI: 10.4236/ijis.2020.102002

29. Sarangi P. K., Verma R., Inder S., Mittal N. Machine learning based hybrid model for gold price prediction in India. In: 2021 9th Int. conf. on reliability, Infocom technologies and optimization (trends and future directions). (ICRITO). (Noida, September 03–04, 2021). New York, NY: IEEE; 2021:1-5. DOI: 10.1109/icrito51393.2021.9596391

30. Oztoprak S., Orman Z. Precious metal prediction by using XAI in the perspective of digital transformation. In: Sandhu K., ed. Emerging challenges, solutions, and best practices for digital enterprise transformation. Hershey, PA: IGI Global; 2021:284-298. DOI: 10.4018/978-1-7998-8587-0.ch015

31. Kangalli Uyar S. G., Uyar U., Balkan E. Fundamental predictors of price bubbles in precious metals: A machine learning analysis. Mineral Economics. 2024;37(1):65-87. DOI: 10.1007/s13563-023-00404-z

32. Alharbi M. H. Applying machine learning techniques to analyze and explore precious metals. Technology and Investment. 2024;15(4):183-197. DOI: 10.4236/ti.2024.154011

33. Yuandong S., Khaskheli A., Raza S. A., Yousufi S. Q. How COVID‑19 influences prices of oil and precious metals: Comparison between data extracted from online searching trends and actual events. Resources Policy. 2022;78:102916. DOI: 10.1016/j.resourpol.2022.102916

34. Karaev A. K., Sidin Ye.G., Gueva L. Kh. Nonlinear dynamics between the price of gold and the US dollar index (2020-2025). Ekonomicheskoe razvitie Rossii = Russian Economic Development. 2025;32(10):257-262. (In Russ.).

35. Karaev A. K., Ponkratov V. V. Nonlinear dynamics of the relationship between the price of gold and the US dollar index. Menedzhment i biznes-administrirovanie = Management and Business Administration. 2025;(3):104-112. (In Russ.). DOI: 10.33983/2075-1826-2025-3-104-112

36. Kolmogorov A. N. On the representation of continuous functions of several variables as superpositions of continuous functions of fewer variables. Doklady Akademii nauk SSSR = Proceedings of the USSR Academy of Sciences. 1956;108(2):179-182. (In Russ.).

37. Kolmogorov A. N. On the representation of continuous functions of several variables by superposition of continuous functions of one variable and addition. Doklady Akademii nauk SSSR = Proceedings of the USSR Academy of Sciences. 1957;114(5):953-956. (In Russ.).

38. Liu Z., Wang Y., Vaidya S., et al. KAN: Kolmogorov-Arnold networks. 2025. DOI: 10.48550/arXiv.2404.19756

39. Cho S.-Y., Lee S., Kim H.-G. Forecasting VIX using interpretable Kolmogorov-Arnold networks. Expert Systems with Applications. 2025;294:128781. DOI: 10.1016/j.eswa.2025.128781

40. Hafver A. Kolmogorov-Arnold networks (KANs) in Wolfram language. Wolfram Community. Aug. 23, 2024. URL: https://community.wolfram.com/groups/-/m/t/3254225

41. Nagpal S. Cryptocurrency price prediction with recurrent neural networks. Wolfram Community. 2022. URL: https://community.wolfram.com/groups/-/m/t/2443748

42. Puoti F., Pittorino F., Roveri M. Quantifying cryptocurrency unpredictability: A comprehensive study of complexity and forecasting. In: AIML Systems’24: Proc. 4th Int. conf. on AI-ML systems. New York, NY: Association for Computing Machinery; 2025:1-8. DOI: 10.1145/3703412.3703420

43. Liu Z., Ma P., Wang Y., Matusik W., Tegmark M. Kan 2.0: Kolmogorov-Arnold networks meet science. 2024. DOI: 10.48550/arXiv.2408.10205

44. Ning L., Dai Z., Fan W., et al. Joint universal adversarial perturbations with interpretations. 2024. DOI: 10.48550/arXiv.2408.01715

45. Sotnikov D. S., Zhuravleva O. V., Varvus S. A., Buevich A. P. The role of gold in the modern economy. Finance: Theory and Practice. 2025;29(2):238-250. DOI: 10.26794/2587-5671-2025-29-2-238-250

46. Belenchuk S. I., Vodianova V. V., Larionova A. D., Minchenkov M. A., Zapletin M. P. Gold price manipulation: Impact on the international monetary system. Finance: Theory and Practice. 2025;29(6):227-242. DOI: 10.26794/2587-5671-2025-29-6-227-242