Politeknik Dergisi 2147-9429 Gazi Üniversitesi 10.2339/politeknik.1438983 Deep Learning Derin Öğrenme Çelik Levha Fiyat Tahmini İçin Esnek Çok Değişkenli Tahmin Modelleri A Comprehensive Analysis of Resilient Multivariate Forecasting Models for Steel Plate Price Prediction https://orcid.org/0000-0003-0436-0372 Alsaideen Mahmud State University of New York at Binghamton https://orcid.org/0000-0003-0632-0905 Ertem Zeynep State University of New York 03 27 2025 28 2 627 637 02 18 2024 04 15 2024 Copyright © 1998, Politeknik Dergisi 1998 Politeknik Dergisi

Büyük bir ekonomik öneme sahip olan küresel çelik endüstrisi, çelik fiyatlarındaki doğal değişkenlik ile karakterize edilmektedir. Emtia Araştırma Birimi'nin (CRU) güvenilir haftalık çelik levha fiyatı verilerinden yararlanan bu araştırma, levha fiyatlarını tahmin etmek için gelişmiş makine öğrenimi algoritmaları kullanıyor. Veri seti 27 Temmuz 2011 ile 5 Temmuz 2023 arasındaki dönemi kapsıyor ve altı temel tahmin faktörünü içeriyor. Özellikle, toplam stok seviyeleri levha fiyatlarıyla en yüksek korelasyonu (0,88) sergilerken, ağır makinelerin nihai ürün stok değeri en etkili faktör olarak ortaya çıkıyor. Makine öğrenimi modelleri için Prophet, XGBoost, LSTM ve GRU'yu içeren kapsamlı bir eğitim rejimi yürütülmektedir. Verilerin zamansal sırasını korumak için Zaman Serisi Çapraz Doğrulama uygulanır ve hiperparametre ayarı için bir Bayesian optimizasyon işlevi kullanıldı. XGBoost, 332,25 ile en düşük Ortalama Karesel Hatayı (MSE) ve 14,55 ile Ortalama Mutlak Hatayı (MAE) sağlayan en iyi performansa sahip model olarak ortaya çıkıyor. %0,94 Ortalama Mutlak Yüzde Hata (MAPE) ve 18,06 Ortalama Karekök Hata (RMSE) puanıyla üstün tahmin doğruluğu sergileyen XGBoost, çelik levha fiyat tahmininde en etkili model olarak kendisini kanıtlıyor. Bu sonuç, gelişmiş tahmine dayalı içgörüler için çelik piyasası dinamiklerinin karmaşıklıklarını yönetmede gelişmiş makine öğrenimi metodolojilerinin etkinliğini vurgulandı.

The global steel industry, holding paramount economic significance, is characterized by the inherent volatility of steel prices. Leveraging the reliable weekly steel plate price data from the Commodity Research Unit (CRU), this research employs sophisticated machine learning algorithms to forecast plate prices. The dataset spans from July 27, 2011, to July 5, 2023, encompassing six key predictive factors. Notably, total inventory levels exhibit the highest correlation (0.88) with plate prices, with the finished goods inventory value of heavy machinery emerging as the most influential factor. A comprehensive training regimen is undertaken for machine learning models, incorporating Prophet, XGBoost, LSTM, and GRU. Time Series Cross-Validation is implemented to maintain the temporal order of the data, and a Bayesian optimization function is employed for hyperparameter tuning. XGBoost emerges as the top-performing model, yielding the lowest Mean Squared Error (MSE) of 332.25 and Mean Absolute Error (MAE) of 14.55. Demonstrating superior predictive accuracy, with a Mean Absolute Percentage Error (MAPE) of 0.94% and a Root Mean Squared Error (RMSE) score of 18.06, XGBoost establishes itself as the most effective model in steel plate price forecasting. This outcome underscores the efficacy of advanced machine learning methodologies in navigating the complexities of steel market dynamics for enhanced predictive insights.

 Machine Learning Steel Forecasting Deep Learning Makina öğrenmesi Çelik Derin öğrenme Tahmin bilimi [1] T. Zhu, X. Wang, Y. Yu, C. Li, Q. Yao, and Y. Li, “Multi-process and multi-pollutant control technology for ultra-low emissions in the iron and steel industry,” Journal of Environmental Sciences, 123:83-95, (2023). [2] John McLean, “History of Western Civilization II: Industrial Revolution,” in History of Western Civilization II, Lumen Learning, (2006). [3] R. Waheeb, “Quality Control of Steel in Steel Iron Product Factory System,” SSRN Electronic Journal, (2023). [4] X. Xu and Y. Zhang, “Regional steel price index forecasts with neural networks: evidence from east, south, north, central south, northeast, southwest, and northwest China,” J Supercomput, 79: 13601:13619, (2023). [5] J. Horák and M. Jannová, “Predicting the Oil Price Movement in Commodity Markets in Global Economic Meltdowns,” Forecasting, 5: 374:389, (2023). [6] A. Page, “Covid-19 Effects on Commodity Pricing,” East Carolina University, (2023). [7] X. Xu and Y. Zhang, “Regional steel price index forecasts with neural networks: evidence from east, south, north, central south, northeast, southwest, and northwest China,” J Supercomput, 79: 13601:13619, (2023). [8] C. J. Haug and J. M. Drazen, “Artificial Intelligence and Machine Learning in Clinical Medicine, 2023,” New England Journal of Medicine, 13: 1201-1208, (2023). [9] S. Makridakis, E. Spiliotis, V. Assimakopoulos, A.-A. Semenoglou, G. Mulder, and K. Nikolopoulos, “Statistical, machine learning and deep learning forecasting methods: Comparisons and ways forward,” Journal of the Operational Research Society, 74: 840-859, (2023). [10] R. Ospina, J. A. M. Gondim, V. Leiva, and C. Castro, “An Overview of Forecast Analysis with ARIMA Models during the COVID-19 Pandemic: Methodology and Case Study in Brazil,” Mathematics, 11(14), (2023). [11] Statista, “World crude steel production from 2012 to 2022.” [12] K. F. Kroner, K. P. Kneafsey, and S. Claessens, “Forecasting volatility in commodity markets,” J Forecast, 14: 77-95, (1995). [13] T. Xiong, C. Li, Y. Bao, Z. Hu, and L. Zhang, “A combination method for interval forecasting of agricultural commodity futures prices”, Knowl Based Syst, 77: 92-102, (2015). [14] R. B. Palazzi, P. Maçaira, E. Meira, and M. C. Klotzle, “Forecasting commodity prices in Brazil through hybrid SSA-complex seasonality models”, Production, 33, (2023). [15] N. Son and Y. Shin, “Short-and Medium-Term Electricity Consumption Forecasting Using Prophet and GRU”, (2023). [16] H. Ben Ameur, S. Boubaker, Z. Ftiti, W. Louhichi, and K. Tissaoui, “Forecasting commodity prices: empirical evidence using deep learning tools”, Ann Oper Res, (2023). [17] K. E. ArunKumar, D. V Kalaga, Ch. M. S. Kumar, M. Kawaji, and T. M. Brenza, “Forecasting of COVID-19 using deep layer Recurrent Neural Networks (RNNs) with Gated Recurrent Units (GRUs) and Long Short-Term Memory (LSTM) cells,” Chaos Solitons Fractals, 146, (2021). [18] T. Chen and C. Guestrin, “Xgboost: A scalable tree boosting system,” in Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining, (2016). [19] H. Oukhouya and K. El Himdi, “Comparing Machine Learning Methods—SVR, XGBoost, LSTM, and MLP—For Forecasting the Moroccan Stock Market,” Computer Sciences & Mathematics Forum, MDPI, (2023). [20] A. K. Gupta, V. Singh, P. Mathur, and C. M. Travieso-Gonzalez, “Prediction of COVID-19 pandemic measuring criteria using support vector machine, prophet and linear regression models in Indian scenario,” Journal of Interdisciplinary Mathematics, 24: 89-108, (2021). [21] T. Kriechbaumer, A. Angus, D. Parsons, and M. Rivas Casado, “An improved wavelet–ARIMA approach for forecasting metal prices”, 39: 32-41, Resources Policy, (2014). [22] Y.-C. Chen, K. S. Rogoff, and B. Rossi, “Can Exchange Rates Forecast Commodity Prices?”, Quarterly Journal of Economics, 125: 1145-1194, (2010). [23] V. I. Kontopoulou, A. D. Panagopoulos, I. Kakkos, and G. K. Matsopoulos, “A review of ARIMA vs. machine learning approaches for time series forecasting in data driven networks”, 15(8), Future Internet, (2023). [24] M. B. Priestley and T. S. Rao, “A test for non-stationarity of time-series,” J R Stat Soc Series B Stat Methodol, 31: 140-149, (1969). [25] A. M. Nyangarika, A. Y. Mikhaylov, and B. Tang, “Correlation of oil prices and gross domestic product in oil producing countries,” International Journal of Energy Economics and Policy, 8: 42-48, (2018). [26] L. Buitinck et al., “API design for machine learning software: experiences from the scikit-learn project,” arXiv preprint arXiv:1309.0238, (2013). [27] C. Shivani, B. Anusha, B. Druvitha, and K. K. Swamy, “RNN-LSTM Model Based Forecasting of Cryptocurrency Prices Using Standard Scaler Transform,” J. Crit. Rev, 10: 144–158, (2022). [28] S. Kamal, “An Analysis of Machine Learning Techniques for Economic Recession Prediction,” (2021).