Altın Fiyatlarını Belirleyen Faktörlerin Makine Öğrenmesi Tabanlı Karşılaştırmalı Analizi

Yıl 2026, Cilt: 42 Sayı: 1 , - , 27.03.2026

Ahmet Yaşar Sürücü , Semra Türkan

https://doi.org/10.65520/erciyesfen.1777185

https://izlik.org/JA97CU87MM

Öz

Bu çalışmada, altın fiyatlarını etkileyen ekonomik faktörleri belirlemek ve en etkili tahmin modelini ortaya koymak amacıyla çeşitli makine öğrenmesi yöntemleri karşılaştırılmıştır. Kullanılan yöntemler arasında doğrusal regresyon, çok değişkenli uyarlamalı regresyon eğrileri (MARS), aşırı gradyan artırma (XGBoost), rastgele orman, yapay sinir ağları (ANN) ve topluluk yaklaşımına dayalı voting regressor yer almaktadır. Test verisi sonuçlarına göre, en yüksek tahmin doğruluğunu MARS modeli göstermiş; MARS modelinden sonra yapay sinir ağları modeli ve voting regressor modeli güçlü performans sergilemiştir. En iyi performans gösteren üç modelin analizi, altın fiyatlarını en çok etkileyen faktörlerin gümüş fiyatı, BIST 100 Endeksi ve NASDAQ Endeksi olduğunu ortaya koymuştur. Genel olarak, makine öğrenmesi yaklaşımları geleneksel modellere göre daha üstün bir performans sergilemiş, MARS modeli ise altın fiyatı tahmininde en güvenilir ve en doğru sonuçları sağlamıştır.

Anahtar Kelimeler

Altın fiyatları , MARS , XGBoost , Makine öğrenmesi

Machine Learning-Based Comparative Analysis of the Determinants of Gold Prices

https://izlik.org/JA97CU87MM

Öz

In this study, various machine learning methods were compared to identify the economic factors influencing gold prices and to determine the most effective prediction model. The methods used include linear regression, multivariate adaptive regression splines (MARS), extreme gradient boosting (XGBoost), random forest, artificial neural networks (ANN), and the ensemble-based voting regressor. According to the test data results, the MARS model demonstrated the highest prediction accuracy, followed by the ANN model and the voting regressor model. The analysis of the three best-performing models revealed that the most influential factors on gold prices are silver prices, the BIST 100 Index, and the NASDAQ Index. Overall, machine learning approaches outperformed traditional models, with MARS providing the most reliable and accurate predictions for gold price forecasting.

Anahtar Kelimeler

Gold prices , MARS , XGBoost , Machine learning

Kaynakça

• [1] Elmas, M., Polat, O. 2014. Determination Demand Faktors of Affecting Gold Price: Period 1988:2013. Journal of Economics and Administrative Sciences, 15(1), 171-187.
• [2] Abar, H. 2020. Prediction of Gold Prices by XGboost and Mars Methods. EKEV Academy Journal, 83, 427-446.
• [3] Özkan, İ., Kolay, Ç. 2016. The Empirical Analysis of the Basic Factors Effecting the Gold Market in Turkey. International Conference on Eurasian Economies, Hungary, 573-582.
• [4] Yüksel, R., Akkoç, S. 2016. Forecasting Gold Prices by Using Artificial Neural Network and an Application. Dogus University Journal, 17(1), 39-50.
• [5] Tursoy, T., Faisal, F. 2018. The impact of gold and crude oil prices on stock market in Türkiye: Empirical evidences from ARDL bounds test and combined cointegration. Resources Policy, 55, 49-54.
• [6] Ojaghlou, M., Rozita, S. 2021. An analysis of the relationship between inflation and gold prices: evidence from Türkiye. Bulletin of Economic Theory and Analysis, 6(2), 79-89.
• [7] Meng, S., Rengifo, E. W., Court, E. 2021. Gold, inflation and exchange rate in dollarized economies – A comparative study of Turkey, Peru and the United States. International Review of Economics and Finance, 71, 82-99.
• [8] Depren, Ö., Kartal, M. T., Depren, S. K. 2021. Changes of gold prices in COVID-19 pandemic: Daily evidence from Türkiye's monetary policy measures with selected determinants. Technological Forecasting and Social Change, 170, 120884.
• [9] Alıcı, V. A., Köseoğlu, M. 2021. Econometric Analysis Of Gold Prices Affecting Factors In Turkey. International Journal of Economics, Business and Politics, 5(2), 254-273.
• [10] Kan, E., Serin, Z. V. 2022. Analysis of cointegration and causality relations between gold prices and selected financial indicators: Empirical evidence from Türkiye. International Journal of Advanced and Applied Sciences, 9(3), 1-9.
• [11] Kilimci, Z. H. 2022. Ensemble Regression-Based Gold Price (XAU/USD) Prediction. Journal of Emerging Computer Technologies, 2(1), 7-12.
• [12] Vargeloğlu, A. A., Özdemir, Y. A. 2023. Examination of Change in Gold Prices with Hidden Markov Model. The Journal of International Scientific Researchers, 8(3), 466-477.
• [13] Badshah, W., Güney, İ., Dobrin, C., Dima, A. 2023. Identifying the Inter-Dynamics Between Gold Prices of Türkiye and Key Economic Indicators: An Application of Three Different Models. Economic Computation and Economic Cybernetics Studies and Research, 57(3), 221-234.
• [14] Qin, M., Su, C. W., Pirtea, M. G., Peculea, A. D. 2023. The essential role of Russian geopolitics: A fresh perception into the gold market. Resources Policy, 81, 103310.
• [15] Beladi, H., Trinh, C. T., Chao, C. C. 2023. Gold prices, cultural factors, and Covid-19 pandemic: An international analysis. Research in International Business and Finance, 66, 102051.
• [16] Cohen, G., Aiche, A. 2023. Forecasting gold price using machine learning methodologies. Chaos, Solitons and Fractals, 175(2), 114079.
• [17] Duman, S., Turnacıgil, S., Arık, E., Aktaş, M. A. 2025. The Role of International Variables in Predicting Gold Prices: Analysis with Machine Learning Algorithms. Sosyoekonomi, 3(63), 103-113.
• [18] Altun, E., Turkan, S. 2016. Analysis of the Better Life Index of OECD Countries with a Multivariate Adaptive Regression Splines Model. International Journal of Statistics and Economics, 17(3), 62-70.
• [19] Friedman, J. H. 1991. Multivariate adaptive regression splines. The Annals of Statistics, 19(1), 1-67.
• [20] Orhan, H., Teke, E. Ç., Karcı, Z. 2018. Application of Multivariate Adaptive Regression Splines (MARS) for Modeling the Lactation Curves. Journal of Agriculture and Nature, 21(3), 363-373.
• [21] Akyol, U., Gül, M. 2025. Predicting of House Sales to Foreigners with Mars Method in Türkiye. The Black Sea Journal of Sciences, 15(1), 498-518.
• [22] Ho, T. K. 1995. Random decision forests. Proceedings of the 3rd International Conference on Document Analysis and Recognition, Montreal, Canada, 1, 278–282.
• [23] Breiman, L. 2001. Random forests. Machine Learning, 45(1), 5–32.
• [24] Chen, T., Guestrin, C. 2016. XGBoost: A scalable tree boosting system. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA, 785–794.
• [25] Haykin, S. 2009. Neural Networks and Learning Machines. 3rd Edition, Pearson Education.