ALTIN FİYATLARININ TAHMİNİNDE MAKİNE ÖĞRENMESİ VE DERİN ÖĞRENME YAKLAŞIMLARI

Abstract

Altın gerek reel gerekse finansal piyasalarda işlem gören önemli bir değer olarak tarih boyunca öncelikli konumunu sürdürmektedir. Bu çalışmada altın fiyatlarının tahmini makine öğrenmesi ve derin öğrenme algoritmaları ile gerçekleştirilmektedir. Analizler sonucunda en iyi tahmin performansına, rassal orman (random forest – RF) algoritması ile ulaşılmıştır. Analiz sonuçlarının yorumlanabilmesi için öznitelik önemi (feature importance) ölçümü de gerçekleştirilmiştir. Buna göre altın fiyatlarının tahmininde en önemli değişkenler sırasıyla altın ile aynı emtia sınıfında yer alan gümüş ve ABD 10 yıllık faiz getirisi olarak belirlenmiştir. Altın fiyatlarının tahmini, bireysel yatırımcılar, kurumsal yatırımcılar ve merkez bankalarının altın rezervleri nedeniyle hükümetler açısından önemlidir. Altın piyasasında fiyatların tahmin edilebilmesi, ilgili piyasanın zayıf formda etkinliği konusunda şüphe uyandırmaktadır.

Keywords

• Altın Fiyat Tahmini
• Derin Öğrenme
• Makine Öğrenmesi
• Öznitelik Önemi
• Piyasa Etkinliği

Supporting Institution

Balıkesir Üniversitesi Bilimsel Araştırma Projeleri Koordinatörlüğü

Project Number

Proje No: 2023/165

Ethical Statement

Etik ihlaline yol açacak herhangi bir durumun olmadığını beyan ederim.

MACHINE LEARNING AND DEEP LEARNING APPROACHES IN FORECASTING GOLD PRICES

Abstract

Gold has historically held a prominent position as a significant asset traded in both real and financial markets. In this study, gold price prediction is performed using machine learning and deep learning algorithms. The best predictive performance was achieved using the random forest (RF) algorithm. Feature importance measurements were also performed to interpret the analysis results. Accordingly, the most important variables in predicting gold prices were identified as silver, which is in the same commodity class as gold, and the US 10-year interest rate, respectively. Forecasting gold prices is important for individual investors, institutional investors, and governments due to the gold reserves held by central banks. The ability to predict prices in the gold market raises doubts about the weak-form efficiency of the relevant market.

Keywords

• Gold Price Prediction
• Deep Learning
• Machine Learning
• Feature Importance
• Market Efficiency

Project Number

Proje No: 2023/165

References

1. Alpaydın, E. (2014). Introduction to Machine Learning. The MIT Press, England.
2. Baker, S. R., Bloom, N. ve Davis, S. J. (2015). “Measuring economic policy uncertainty”, NBER Working Paper No. 21633. National Bureau of Economic Research.
3. Balcilar, M., Gupta R., ve Pierdzioch, C. (2016). “Does uncertainty move the gold price? New evidence from a nonparametric causality-in-quantiles test”, Resources Policy, 49, 74-80.
4. Basher, S. A. ve Sadorsky, P. (2022). “Forecasting Bitcoin price direction with random forests: How important are interest rates, inflation, and market volatility?”, Machine Learning with Applications, 9, 100355.
5. Bilgin, M. H., Gozgor, G., Lau, C. K. M. ve Sheng, X. (2018). “The effects of uncertainty measures on the price of gold”, International Review of Financial Analysis, 58, 1-7.
6. Boser, B. E, Guyon, I. M. ve Vapnik, V. N. (1992). “A training algorithm for optimal margin classifiers”, Proceedings of the Fifth Annual Workshop on Computational Learning Theory, COLT '92. New York, USA. 144-152.
7. Breiman, L. (2001). “Random forests”, Machine Learning, 45(1), 5–32.
8. Chen, T. ve Guestrin, C. (2016). “XGBoost: A scalable tree boosting system”, In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (s. 785–794). Association for Computing Machinery.

9. Cohen, G. ve Aiche A. (2022). “Forecasting gold price using machine learning methodologies”, Chaos, Solitons & Fractals. 175(2), 114079.
10. Çavdaroğlu, G. Ç. ve Arık, A. O. (2024). “Topluluk Öğrenmesi”, Makine Öğrenmesi Algoritmaları içinde (Editör: M. Gök) (s. 251-280). Nobel Yayıncılık, Ankara.
11. Das, S., Sahu, T. P. ve Janghel, R. R. (2022). “Oil and gold price prediction using optimized fuzzy inference system based extreme learning machine”, Resources Policy, 79, 103109.
12. Duman, S., Turnacıgil, S., Arık, E. ve Aktaş, M. A. (2025). “The role of international variables in predicting gold prices: Analysis with machine learning algorithms”, Sosyoekonomi, 33(63), 103-113.
13. Fama, E. (1965). “Random walks in stock market prices”, Financial Analysts Journal, 21(5), 55-59.
14. Fama, E. (1970). “Efficient markets: A review of theory and empirical work”, Journal of Finance, 25, 1181-1185.
15. Fang, L., Yu, H. ve Xiao, W. (2018). “Forecasting gold futures market volatility using macroeconomic variables in the United States”, Economic Modelling, 72, 249-259.
16. Géron, A. (2019). Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems, O’Reilly Media, Canada.
17. Gers, F. A., Schmidhuber, J. ve Cummins, F. (2000). “Learning to forget: Continual prediction with LSTM”, Neural Computation, 12(10), 2451–2471.
18. Hochreiter, S. ve Schmidhuber, J. (1997). “Long short-term memory”, Neural Computation, 9(8), 1735–1780.
19. Hull, I. (2021). Machine Learning for Economics and Finance in TensorFlow 2: Deep Learning Models for Research and Industry. Apress Media, New York.
20. İncekara, B. ve İncekara, R. (2016). “Dünya altın piyasaları”, Nişantaşı Üniversitesi Sosyal Bilimler Dergisi, 4(2), 116-147.
21. Kahneman, D. ve Tversky, A. (1979). “Prospect theory: An analysis of decision under risk”, Econometrica, 47(2), 263-292.
22. Kangalli Uyar, S. G., Uyar, U. ve Balkan, E. (2024). “Fundamental predictors of price bubbles in precious metals: A machine learning analysis”, Mineral Economics, 37, 65-87.
23. Kristjanpoller, W. ve Minutolo, M. C. (2015). “Gold price volatility: A forecasting approach using the artificial neural network-GARCH model”, Expert Systems with Applications, 42(20), 7245-7251.
24. Livieris, I. E., Pintelas, E., & Pintelas, P. (2020). “A CNN – LSTM model for gold price time-series forecasting”, Neural Computing and Applications, 32, 17351–17360.
25. Madziwa, L., Pillalamarry, M. ve Chatterjee, S. (2022). “Gold price forecasting using multivariate stochastic model”, Resources Policy, 76, 102544.
26. Malliaris, A. G. ve Malliaris, M. (2013). “Are oil, gold and the euro inter-related? Time series and neural network analysis”, Review of Quantitative Finance and Accounting, 40(1), 1-14.
27. Malliaris, A. G. ve Malliaris, M. (2015). “What drives gold returns? A decision tree analysis”, Finance Research Letters, 13, 45-53.
28. Mensi, W., Beljid, M., Boubaker, A. ve Managi, S. (2013). “Correlations and volatility spillovers across commodity and stock markets: Linking energies, food, and gold”, Economic Modelling, 32, 15-22.
29. Müller, A. C., & Guido, S. (2017). Introduction to machine learning with Python: A guide for data scientists. O’Reilly Media, USA.
30. Özdemir, M. (2020). “R ile Programlama ve Makine Öğrenmesi” (Ed: Y. Çelikbilek). Nobel Akademik Yayıncılık, Ankara.
31. Pattnaik, D., Hassan, M. K., DSousa, A. ve Ashraf, A. (2023). “Investment in gold: A bibliometric review and agenda for future research”, Research in International Business and Finance, 64, 101854.
32. Ping, P. Y., Ahmad, M. H. B. ve Ismail, N. B. (2016). “Volatility spillover effect study in US dollar and gold market based on bivariate-BEKK model”, 23rd Malaysian National Symposium of Mathematical Sciences: Advances in Industrial and Applied Mathematics, Johor Bahru; Malaysia.
33. Qadan, M. (2019). “Risk appetite and the prices of precious metals”, Resources Policy, 62, 136-153.
34. Qian, Y., Ralescu, D. A. ve Zhang, B. (2019). “The analysis of factors affecting global gold price”, Resources Policy, 64, 101478.
35. Risse, M. (2019). “Combining wavelet decomposition with machine learning to forecast gold returns”, International Journal of Forecasting, 35(2), 601–615.
36. Shahzad, S. J. H., Raza, N., Balcilar, M., Ali, S. ve Shahbaz, M. (2017). “Can economic policy uncertainty and investors sentiment predict commodities returns and volatility?”, Resources Policy, 53, 208-218.
37. Swamy, V. ve Lagesh, M. A. (2023). “Does happy twitter forecast gold price?”, Resources Policy, 81(C), 103299.
38. Tripurana, N., Kar, B., Chakravarty, S., Paikaray, B. K. ve Satpathy, S. (2022). “Gold price prediction using machine learning techniques”, https://ceur-ws.org/Vol-3283/Paper108.pdf (Erişim Tarihi: 02.07.2025).
39. Tversky, A. ve Kahneman, D. (1974). “Judgment under uncertainty: Heuristics and biases”, Science, 185(4157), 1124-1131.
40. World Gold Council (2025). Central Bank Gold Reserves Survey 2025. https://www.gold.org/goldhub/research/central-bank-gold-reserves-survey-2025 (Erişim Tarihi: 30.06.2025).
41. Yang, M., Wang, R., Zeng, Z. ve Li, P. (2024). “Improved prediction of global gold prices: An innovative hurst-reconfiguration-based machine learning approach”, Resources Policy, 88, 104430.
42. Yüksel, R. ve Akkoç, S. (2016). “Altın fiyatlarının yapay sinir ağları ile tahmini ve bir uygulama”, Doğuş Üniversitesi Dergisi, 17(1), 39-50.