MAKİNE ÖĞRENMESİNDE REGRESYON MODELLERİNİN TAHMİN PERFORMANSLARININ KARŞILAŞTIRILMASI: TÜRKİYE ÜRÜN İHTİSAS BORSASI BUĞDAY ENDEKSİ ÜZERİNE BİR UYGULAMA

Yıl 2023, Cilt: 11 Sayı: 2, 602 - 623, 31.12.2023

Hasan Arda Burhan

https://doi.org/10.52122/nisantasisbd.1377642

Öz

Tarımsal emtia fiyatları, maliye ve para politikalarında farklılaşma ve düzenlemelere yol açarak ekonomiler üzerinde önemli etkiler yaratmakta, özellikle gelişmekte olan ülkelerde hanehalkı ekonomilerini ve satın alma gücünü de etkilemektedirler. Bu fiyatlarındaki istikrarsızlık ve değişkenlik bu ekonomiler üzerinde olumsuz etkilere de neden olmaktadır. Öte yandan, emtia piyasalarındaki varlıklar tahvil ve hisse senetleri gibi popüler hale gelmiştir. Bu nedenle ortaya çıkan risk yönetimi, istikrarlı fiyatlama ve işlem maliyetlerini düşürme ihtiyaçları, ülkelerde ticaret borsalarının kurulmasına yol açmıştır. Gelişmekte olan bir ülke olan Türkiye’de kurulan Türkiye Ürün İhtisas Borsası (TÜRİB) aracılığıyla Elektronik Ürün Senedi (ELÜS) ticaretinin yapılabilmesi böylece mümkün hale gelmiştir. Bu çalışmada, farklı makine öğrenmesi regresyon tekniklerinin tahmin performansları, TÜRİB Buğday Endeksi (TRBBGD) tahmininde ABD Doları-Türk Lirası kuru (USD/TRY), Brent ham petrol fiyatları, gecelik faiz oranını içeren bir model ve 01/04/2021-20/02/2023 dönemi günlük verileri kullanılarak değerlendirilmiştir. Gerçek değerlerle karşılaştırma ve çeşitli performans değerlendirme kriterleri kullanılarak yapılan incelemelere göre tüm yöntemlerin başarılı sonuçlar verdiği, öte yandan ağaç tabanlı makine öğrenmesi yöntemlerinin diğer yaklaşımlara kıyasla daha iyi genel performans gösterdiği ifade edilebilmektedir.

Anahtar Kelimeler

Emtia Piyasaları, Elektronik Ürün Senedi (ELÜS), TÜRİB, Makine Öğrenmesi Regresyon

COMPARISON OF PREDICTION PERFORMANCES OF REGRESSION MODELS IN MACHINE LEARNING: AN APPLICATION ON THE TURKISH MERCANTILE EXCHANGE WHEAT INDEX

Öz

Agricultural commodity prices have significant impacts on economies by leading to changes and regulations in both fiscal and monetary policies. These also have effects on household economies and consumer purchasing power particularly in developing countries. Thereby, instability and variability in these prices constitute adverse effects on these economies. On the other hand, assets of the commodity markets become popular just as bonds and stocks. Because of this growing interest, needs for managing risks, stable prices and lowering transaction costs has led to establishment of the commodity exchanges. In this context, Turkey put the licensed warehousing system into operation by founding the Turkish Mercantile Exchange (TMEX) to operate trades of Electronic Warehouse Receipts (EWRs). In this study, a model including US Dollar-Turkish Lira exchange rate (USD/TRY), Brent crude-oil prices, overnight interest rate and a daily dataset for the 01/04/2021-20/02/2023 period were used to assess several machine learning regression methods in predicting the TMEX Wheat Index (TMXWHT). As verified by comparisons with actual values and considering performance evaluation criteria, all methods yielded successful outcomes, furthermore, tree-based methods revealed better overall performance.

Anahtar Kelimeler

Commodity Markets, Electronic Warehouse Receipts (EWRs), TMEX, Machine Learning Regression

Kaynakça

• Alpaydin, E. (2004). Introduction to Machine Learning. Cambridge: The MIT Press.
• Amin, M.N. (2020). "Predicting Price of Daily Commodities Using Machine Learning", International Conference on Innovation and Intelligence for Informatics, Computing and Technologies (3ICT) (s. 1-6). Bahrain: IEEE.
• Araújo, S.O., Peres, R.S., Barata, J., Lidon, F., and Ramalho, J.C. (2021). "Characterising the Agriculture 4.0 Landscape—Emerging Trends, Challenges and Opportunities", Agronomy , 11(4), 667-704.
• Aydın, A. (2021). "Elektronik Ürün Senedi (ELÜS) ve İslam Hukuku Açısından Tahlili", Ticaret ve Fikri Mülkiyet Hukuku Dergisi, 7(1), 21-36.
• Barnard, A., and Opletal, G. (2020). "Selecting Machine Learning Models for Metallic Nanoparticles", Nano Futures, 4(3),035003,1-13.
• Basak, D., Pal, S., and Patranabis, D.C. (2007). "Support Vector Regression", Neural Information Processing, 11(10), 203-224.
• Ben Ameur, H., Boubaker, S., Ftiti, Z., Louhichi, W., and Tissaoui, K. (2023). "Forecasting Commodity Prices: Empirical Evidence Using Deep Learning Tools", Annals of Operations Research, 1-19.
• Bork, L., Kaltwasser, P.R., and Sercu, P. (2019). "Commodity Index Construction and the Predictive Power of Exchange Rates", Journal of Banking and Finance, 1-49.
• Brownlee, J. (2017). Master Machine Learning Algorithms. Retrieved from: https://machinelearningmastery.com/master-machine-learning-algorithms/.
• Chen, Z., Yan, B., and Kang, H. (2022). "Dynamic Correlation Between Crude Oil and Agricultural Futures Markets", Review of Development Economics, 26(3), 1798-1849.
• Çayır, C. (2019). Elektronik Ürün Senetlerinin Tarımsal Fiyatlara Etkisi: Türkiye Örneği. (Yayınlanmamış) Yüksek Lisans Tezi, İstanbul: İstanbul Üniversitesi Sosyal Bilimler Enstitüsü.
• De Myttenaere, A., Golden, B., Le Grand, B., and Rossi, F. (2016). "Mean Absolute Percentage Error for Regression Models", Neurocomputing, 192, 38-48.
• Deisenroth, M.P., Faisal, A.A., and Ong, C.S. (2020). Mathematics for Machine Learning. Cambridge: Cambridge University Press.
• Dias, J., and Rocha, H. (2019). "Forecasting Wheat Prices Based on Past Behavior: Comparison of Different Modelling Approaches", in Computational Science and Its Applications–ICCSA 2019: 19th International Conference. Computational Science and Its Applications–ICCSA 2019: 19th International Conference Proceedings, Part III (s. 167-182). Saint Petersburg: Springer.
• Díaz, G., Coto, J., and Gómez-Aleixandre, J. (2019). "Prediction and Explanation of the Formation of the Spanish Day-Ahead Electricity Price Through Machine Learning Regression", Applied Energy, 239, 610-625.
• Doğan, Z., and Özulucan, A. (2023). "Lisanslı Depoculuk Sistemi ve Elektronik Ürün Senetleri ile İlgili Sağlanan Vergi ve Diğer Mali Destekler", Vergi Raporu,, 281, 42-56.
• Dörtok, A., and Aksoy, A. (2018). "Türkiye Buğday Sektörünün Eşanlı Model Yöntemiyle Tahmini", Kahramanmaraş Sütçü İmam Üniversitesi Tarım ve Doğa Dergisi, 21(4), 580-586.
• Eleje, E. O., Josaphat, U.O., and Nwokeji, N.N. (2008). "Commodity Exchange Markets and Economic Development", Nigerian Journal Of Banking And Finance, 8, 132-146.
• Etienne, X.L. (2015). "Financialization Of Agricultural Commodity Markets: Do Financial Data Help To Forecast Agricultural Prices?", 2015 Agricultural and Applied Economics Association and Western Agricultural Economics Association Annual Meeting, (pp. 1-38). San Francisco.
• FAO (2016). The State of Food and Agriculture: Climate Change, Agriculture and Food Security, Rome.
• FAO (2017). The Future of Food and Agriculture: Trends and Challenges, Rome.
• Frank, J., and Garcia, P. (2010). "How Strong are the Linkages Among Agricultural, Oil, and Exchange Rate Markets?", Proceedings of the NCCC-134 Conference on Applied Commodity Price Analysis. St. Louis : NCCC.
• Gabriel, H.D. (2012). "Warehouse Receipts and Cecuritization in Agricultural Finance", Uniform Law Review , 17(1-2). 369-376.
• Gargano, A., and Timmermann, A. (2014). "Forecasting Commodity Price Indexes Using Macroeconomic and Financial Predictors", International Journal of Forecasting, 30(3), 825-843.
• Géron, A. (2019). Hands-on Machine Learning with Scikit-learn, Keras, and Tensorflow. Sebastopol: O’Reilly Media, Inc..
• Giraka, O., and Selvaraj, V.K. (2020). "Short-term Prediction of Intersection Turning Volume Using Seasonal ARIMA Model", Transportation Letters, 12(7), 483-490.
• Gospodinov, N., and Jamali, I. (2018). "Monetary Policy Uncertainty, Positions of Traders and Changes in Commodity Futures Prices", European Financial Management, 24(2), 239-260.
• Göleç, A., Murat, A., Tokat, E., and Türkşen, İ.B. (2012). "Forecasting Model of Shanghai and CRB Commodity Indexes", Expert Systems with Applications, 39(10), 9275-9281.
• Gün, N., and Tahsin, E. (2019). "Role of Electronic Warehouse Receipt System in Development of Commodity Exchanges: An Assessment For Turkey", Tarım Ekonomisi Araştırmaları Dergisi, 5(1), 9-24.
• Harris, J. (2017). A Machine Learning Approach To Forecasting Consumer Food Prices. Nova Scotia: Halifax.
• Hatzenbuehler, P. L., Abbott, P. C., and Foster, K.A. (2016). "Agricultural Commodity Prices and Exchange Rates Under Structural Change", Journal of Agricultural and Resource Economics, 41(2), 204-224.
• Hernandez, J.A., Kang, S.H., and Yoon, S.-M. (2021). "Spillovers and Portfolio Optimization of Agricultural Commodity and Global Equity Markets", Applied Economics, 53(12), 1326-1341.
• Hung, N.T. (2021). "Oil Prices and Agricultural Commodity Markets: Evidence from Pre and During COVID-19 Outbreak", Resources Policy , 73, 102236.
• Ismail, A., Ihsan, H., Khan, S. A., and Jabeen, M. (2017). "Price Volatility of Food and Agricultural Commodities: A Case Study of Pakistan", Journal of Economic Cooperation and Development, 38(3), 77-120.
• İlarslan, K., and Yıldız, M. (2022). "Do International Agricultural Commodity Prices Have an Effect on the Stock Market Index? A Comparative Analysis Between Poland and Turkey", Sosyoekonomi, 30(52), 87-107.
• İlter Küçükçolak, N. (2022). "Ürün İhtisas Borsacılığının Gıda Fiyat İstikrarına Katkısı", Pamukkale Üniversitesi Sosyal Bilimler Enstitüsü Dergisi, 49, 325-339.
• Karabaş, S., and Gürler, A.Z. (2010). "Lisanslı Depoculuk Sisteminin İşleyişi ve Türkiye’de Uygulanabilirliği", Sosyal Bilimler Araştırmaları Dergisi, 5(1), 196-210.
• Kayral, İ.E., and Aksoy, L. (2022). "Yeni Gıda Endekslerinde Haftanın Günü Etkisi Var Mı?", IBAD Sosyal Bilimler Dergisi, 12, 461-476.
• Kern, M. (2002). "Food, Feed, Fibre, Fuel and Industrial Products of the Future: Challenges and Opportunities, Understanding the Strategic Potential of Plant Genetic Engineering", Journal of Agronomy and Crop Science, 188, 291-305.
• Khanal, S., Fulton, J., Klopfenstein, A., Douridas, N., and Shearer, S. (2018). "Integration of High Resolution Remotely Sensed Data and Machine Learning Techniques for Spatial Prediction of Soil Properties and Corn Yield", Computers and Electronics in Agriculture, 153, 213-225.
• Kılıçarslan, A., and Sucu, M.Ç. (2021). "Ticaret Borsası ve Ürün İhtisas Borsasında İşlem Maliyetleri: Karşılaştırmalı Bir Uygulama", Sakarya İktisat Dergisi, 10(3), 257-274.
• Liakos, K.G., Busato, P., Moshou, D., Pearson, S., and Bochtis, D. (2018). "Machine Learning in Agriculture: A Review", Sensors, 18(8), 2674-2703.
• Lin, A.Y., ZHANG, M., and SELPI, S. (2018). "Using Scaling Methods to Improve Support Vector Regression’s Performance for Travel Time and Traffic Volume Predictions", in I. Rojas, H. Pomares and O. Valenzuela (Eds.). Time series analysis and forecasting ITISE 2017 contributions to statistics (s. 115-127 ). Paper Presented at International Work-Conference on Time Series Analysis, Cham: Springer. https://doi.org/10.1007/978-3-319-96944-2_8.
• Liu, B., Hui, H., and Li, J. (2013). "The Research of Commodity E-Commerce and Logistics Collaborative System Based on the Electronic Warehouse Receipts", Proceedings of 3rd International Conference on Logistics, Informatics and Service Science (s. 659-666). Reading: Springer.
• Liu, N., and Yu, J. (2019). "Raw Grain Price Forecasting with Regression Analysis", 2019 International Conference on Modeling, Simulation and Big Data Analysis (MSBDA 2019) (s. 372-378.). Dordrecht: Atlantis Press.
• Maabreh, M. and Almasabha, G. (2023). "Machine Learning Regression Algorithms for Shear Strength Prediction of SFRC-DBs: Performance Evaluation and Comparisons", Arabian Journal for Science and Engineering.
• Matloff, N. (2017). Statistical Regression and Classification-From Linear Models to Machine Learning. Boca Raton: CRC Press.
• Maulud, D.H., and Abdulazez, A. M. (2020). "A Review on Linear Regression Comprehensive on Machine Learning", Journal of Applied Sciences and Technology Trends, 1(4), 140-147.
• Melichar, M., and Atems, B. (2019). "Global Crude Oil Market Shocks and Global Commodity Prices", OPEC Energy Review, 43(1), 92-105.
• Miller, J. D. (2017). Statistics for Data Science. Birmingham: Packt Publishing.
• Mollaahmetoğlu, E., and Yaşar Akçali, B. (2022). "Elektronik Ürün Senedi (ELÜS) Endeksleri ile ABD Dolar Endeksi ve Dolar Kuru Arasındaki İlişkinin Simetrik ve Asimetrik Nedensellik Testleri ile Analizi", Ekonomi Politika ve Finans Araştırmaları Dergisi, 7(IERFM Özel Sayısı), 45-60.
• Murphy, K. P. (2012). Machine Learning - A Probabilistic Perspective. Cambridge: The MIT Press.
• Nagarajan, S., Feyisa, T., and Degefa, T. (2021). "Forecasting Retail Price of Consumer Food Product’s: In the Case of Oromia Region, Ethiopia", Journal of Tianjin University Science and Technology, 54(7), 629-646.
• Nazlioglu, S., Erdem, C., and Soytas, U. (2013). "Volatility Spillover Between Oil and Agricultural Commodity Markets", Energy Economics, 36, 658-665.
• Nyarko, Y., and Pellegrina, H. S. (2022). "From Bilateral Trade to Centralized Markets: A Search Model for Commodity Exchanges in Africa", Journal of Development Economics, 157, 102867.
• Özçelik, A., and Özer, O. O. (2006). "Koyck Modeliyle Türkiye’de Buğday Üretimi ve Fiyatı İlişkisinin Analizi", Journal of Agricultural Sciences, 12(04), 333-339.
• Özsoy Çalış, N., Babuşçu, Ş., and Hazar, A. (2022). "Bir Tarımsal Kredi Olarak ELÜS Rehni Karşılığında Kredi Kullandırımı", Gümrük ve Ticaret Dergisi, 9(27), 25-41.
• Pajankar, A., and Joshi, A. (2022). Hands-on Machine Learning with Python: Implement Neural Network Solutions with Scikit-learn and PyTorch. New York: Apress.
• Paper, D. (2020). Hands-on Scikit-Learn for Machine Learning Applications - Data Science Fundamentals with Python. Logan: Apress.
• Paris, A. (2018). "On the Link Between Oil and Agricultural Commodity Prices: Do Biofuels Matter?", International Economics, 155, 48-60.
• Polat, K. (2022). Durum ve Tahmin: Buğday 2021/2022, Ankara.
• Powell, N., Ji, X., Ravash, R., Edlington, J., and Dolferus, R. (2012). "Yield Stability for Cereals in a Changing Climate", Functional Plant Biology, 39(7), 539-552.
• Pozez, A.M. (2016). "A Roadmap to Better Understanding the Issuance and Transfer of Negotiable Electronic Warehouse Receipts in the American Cotton Trade", Arizona Journal of International and Comparative Law, 33: 205-218.
• Raschka, S., Liu, Y., and Mirjalili, V. (2022). Machine Learning with Pytorch and Scikit-learn - Develop Machine Learning and Deep Learning Models with Python. Birmingham: Packt Publishing Ltd..
• Rashid, M., Bari, B.S., Yusup, Y., Kamaruddin, M.A., and Khan, N. (2021). "A Comprehensive Review of Crop Yield Prediction Using Machine Learning Approaches with Special Emphasis on Palm Oil Yield Prediction", IEEE Access, 9, 63406-63439.
• Rezitis, A.N. (2015). "The Relationship Between Agricultural Commodity Prices, Crude Oilprices and US Dollar Exchange Rates: A Panel VAR Approach and Causality Analysis", International Review of Applied Economics, 29(3), 403-434.
• Roy, D., and Bhar, R. (2020). "Trend of Commodity Prices and Exchange Rate in Australian Economy: Time Varying Parameter Model Approach", Asia-Pacific Financial Markets, 27, 427-437.
• Shalev-Shwartz, S., and Ben-David, S. (2014). Understanding Machine Learning: From Theory to Algorithms. New York: Cambridge University Press.
• Song, L., Tian, G., and Jiang, Y. (2022). "Connectedness of Commodity, Exchange Rate and Categorical Economic Policy Uncertainties — Evidence from China", North American Journal of Economics and Finance , 60, 101656.
• Song, Q.C., Tang, C., and Wee, S. (2021). "Making Sense of Model Generalizability: A Tutorial on Cross-Validation in R and Shiny", Advances in Methods and Practices in Psychological Science, 4(1), 2515245920947067.
• Sun, Y., Guo, J., Shan, S., and Khan, Y.A. (2021). "Wheat Futures Prices Prediction in China: A Hybrid Approach", Discrete Dynamics in Nature and Society, 1-9.
• Tiwari, A.K., Khalfaoui, R., Solarin, S.A., and Shahbaz, M. (2018). "Analyzing the Time-Frequency Lead–Lag Relationship Between Oil and Agricultural Commodities", Energy Economics, 76, 470-494.
• TMEX. (2022). “Turkish Mercantile Exchange”, https://www.turib.com.tr/en/indices/ adresinden alındı
• UNCTAD. (2009). Development Impacts of Commodity Exchanges in Emerging Markets, New York.
• Vancsura, L., Tatay, T., and Bareith, T. (2023). "Evaluating the Effectiveness of Modern Forecasting Models in Predicting Commodity Futures Prices in Volatile Economic Times", Risks, 11(2), 27-43.
• Wang, Q., and Hu, Y. (2015). "Cross-correlation Between Interest Rates and Commodity Prices", Physica A: Statistical Mechanics and its Applications, 428, 80-89.
• Wang, Y., Liu, L., and Wu, C. (2020). "Forecasting Commodity Prices Out-Of-Sample: Can Technical Indicators Help?", International Journal of Forecasting, 36(2), 666-683.
• Willmott, C.J., and Matsuura, K. (2005). “Advantages of the Mean Absolute Error (MAE) Over the Root Mean Square Error (RMSE) in Assessing Average Model Performance”, Climate Research, 30(1), 79-82.
• Worku, M.A., Ejigu, A., and Gebresilasie, G. (2016). "The Contribution of Ethiopia Commodity Exchange for Promoting Exports of Agricultural Products", Journal of Economics and Sustainable Development, 7(9), 81-90.
• Xu, M., Watanachaturaporn, P., Varshney, P.K. and Arora, M.K. (2005). "Decision Tree Regression for Soft Classification of Remote Sensing Data", Remote Sensing of Environment, 97, 322-336.
• Xu, X., and Zhang, Y. (2022). "Commodity Price Forecasting Via Neural Networks for Coffee, Corn, Cotton, Oats, Soybeans, Soybean Oil, Sugar, and Wheat", Intelligent Systems in Accounting, Finance and Management, 29(3), 169-181.