MODELING AND FORECASTING GLOBAL AGRICULTURAL COMMODITY PRICES USING HYBRID MODELS

Abstract

In recent years, rare events such as the COVID-19 pandemic and the Russia–Ukraine war have caused disruptions in global agricultural commodity supply chains, especially through supply and demand imbalances. As a result, unusual price fluctuations have been observed in commodity markets. In such periods, accurate modeling and forecasting of agricultural commodity prices is important to keep the agricultural sector sustainable for both national economies and individual investors. In this study, the performance of several methods used to model financial time series with rare and low-probability events is compared. These methods include the Generalized Autoregressive Conditional Heteroskedasticity (GARCH) model, the State Space Model (SSM), Long Short-Term Memory (LSTM) neural networks, and hybrid GARCH-LSTM models. The analysis uses weekly global agricultural commodity prices for wheat, sugar, cocoa, coffee, cotton, corn, soybean, and oats from March 2001 to December 2025. The results show that the State Space Model demonstrates significantly superior performance in both price modeling and future forecasting.

Keywords

• Agricultural commodity prices
• Machine learning
• State space model
• Global rare events

Supporting Institution

Eskisehir Osmangazi University Scientific Research Fund (ESOGU BAP)

Project Number

FBA-2025-3333

Ethical Statement

No Need/Not Applicable

MODELING AND FORECASTING GLOBAL AGRICULTURAL COMMODITY PRICES USING HYBRID MODELS

Abstract

Son yıllarda, dünyada COVID-19 pandemisi ve Rusya-Ukrayna savaşı gibi nadiren görülen olayların etkisiyle özellikle dünyadaki tarımsal emtia tedarik zincirlerinde arz-talep dengesizlikleri gibi aksaklıklar gözlemlenmiştir. Bu gelişmeler sonucunda emtia fiyatlarında olağandışı dalgalanmalar (volatilite) gözlemlenmiştir. Bu gibi durumlarda, tarım sektörünün hem ülke ekonomileri hem de bireysel yatırımcılar açısından sürdürülebilir olması için tarımsal emtia fiyatlarının modellenmesi ve gelecek tahmininin en az hata payı ile yapılması önem taşımaktadır. Nadiren görülen düşük olasılıklı olayları içeren finansal zaman serilerinin modellenmesinde ve gelecek tahminlerinin yapılmasında yenilik olarak genelleştirilmiş otoregresif koşullu değişen varyans (GARCH), durum uzay modeli (State Space Model, SSM), uzun kısa süreli bellek (Long Short-Term Memory, LSTM) yapay sinir ağları ve Hibrit GARCH-LSTM modellerinin performans karşılaştırmaları yapılmıştır. Bu projede, Mart 2001 ile Aralık 2025 tarihleri arasındaki dünya tarımsal emtia haftalık fiyatlarından; buğday, şeker, kakao, kahve, pamuk, mısır, soya ve yulaf fiyatları kullanılmıştır. Sonuç olarak, durum uzay modelinin (State Space Model), modelleme ve gelecek tahmini konusunda açık olarak iyi performans göstermiştir.

Keywords

• Tarımsal Emtia Fiyatları
• Makine Öğrenmesi
• Durum Uzay Modeli
• Küresel Nadir Olaylar

Project Number

FBA-2025-3333

References

1. Akar, Ö., Akar. A., and Bayata, H. F. (2026) “Identifying Agricultural Crops with Similar Spectral Properties Using Machine Learning Classifiers and Sensefly Ebee SQ Multispectral UAV Images”, Journal of Agricultural Sciences, 32(1): 93-111.
2. Amin, M. D., Badruddoza, S., and Sarasty, O. (2024) “Comparing the Great Recession and COVID‐19 Using Long Short‐Term Memory: A Close Look Into Agricultural Commodity Prices”, Applied Economic Perspectives and Policy, 68(2): 1211.
3. Avinash. G., Ramasubramanian, V., Ray, M., Paul, R. K., Godara, S., Nayak, G. H. H., Kumar, R. R., Manjunatha, B., Dahiya, S., and Iquebal, M. A. (2024) “Hidden Markov Guided Deep Learning Models for Forecasting Highly Volatile Agricultural Commodity Prices”, Applied Soft Computing, 158: 111557.
4. Apergis, N. and Rezitis, A. (2003) “Agricultural Price Volatility Spillover Effects: The Case of Greece”, European Review of Agricultural Economics, 30 (3): 389–406.
5. Azhar, R., Kusuma, Wisnu, F., Satria, Dwi, Kesuma, F., Rizki, Eka, Putri, W., and Andri, Prasetya, R. (2022) “State-Space Implementation in Forecasting Carbon and Gas Prices in Commodity Markets”, International Journal of Energy Economics and Policy, 12(3): 280–286.
6. Bahdanau, D., Cho, K., and Bengio, Y. (2014) “Neural Machine Translation by Jointly Learning to Align and Translate”, arXiv preprint arXiv:1409.0473.
7. Bollerslev, T. (1986) “Generalized Autoregressive Conditional Heteroskedasticity”, Journal of Econometrics, 31(3): 307-327.
8. Celik, B. A. and Celik, S. (2025) “Hybrid Forecasting of Agricultural Commodity Prices: Integrating Machine Learning, Time Series, and Stochastic Simulation Models”, Borsa Istanbul Review.

9. Cromwell, J. B. (2004)“Chaotic price dynamics of agricultural commodities.” Graduate Unpublished Theses, Dissertations, and Problem Reports, 2108.
10. Goodfellow, I., Bengio, Y., and Courville, A. (2016) “Deep Learning”, MIT Press.
11. Gu, S. and Li, M. (2024) “Forecasting.corn Futures Prices Using the LSTM Model” Financial Economics Research, 1(1): 1–16.
12. He, K., Zhang, X., Ren, S., and Sun, J. (2016) “Deep Residual Learning for Image Recognition”, Proceedings of the IEEE conference on computer vision and pattern recognition: 770-778.
13. Hochreiter, S. and Schmidhuber, J. (1997) “Long Short-Term Memory”, Neural computation, 9(8): 1735.
14. Huber, P. J. (1964) “Robust Estimation of a Location Parameter”, The Annals of Mathematical Statistics, 35(1): 73-101.
15. Kakade, K., Mishra, A. K., Ghate, K., and Gupta, S. (2022) “Forecasting Commodity Market Returns Volatility: A Hybrid Ensemble Learning GARCH‐LSTM Based Approach”, Intelligent Systems in Accounting, Finance and Management, 29 (2):103–117.
16. Kalman, R. E. (1960)“A New Approach to Linear Filtering and Prediction Problems”, Transactions of the ASME–Journal of Basic Engineering, 82, Series D: 35–45.
17. Kim, B-J. and Nam, I-W. (2025) “A Review of Hybrid LSTM Models in Smart Cities”, Processes, 13(7): 2298.
18. Kim, H. Y. and Won, C. H. (2018) “Forecasting the Volatility of Stock Price Index: A Hybrid Model İntegrating LSTM with Multiple GARCH-Type Models” Expert Systems with Applications, 103: 25-37.
19. Kingma, D. P. and Ba, J. (2014) “Adam: A Method for Stochastic Optimization”, arXiv preprint arXiv:1412:6980.
20. Maas, A. L., Hannun, A. Y., and Ng, A. Y. (2013) “Rectifier Nonlinearities Improve Neural Network Acoustic Models”, Proc. ICML, 30(1): 3.
21. Manera, M., Nicolini, M., and Vignati, I. (2013) “Futures Price Volatility in Commodities Markets: The Role of Short Term vs Long Term Speculation”, Fondazione Eni Enrico Mattei Working, Papers, Paper 796.
22. Manogna, R.L., Dharmaji, V., and Sarang, S. (2025) “A Novel Hybrid Neural Network-Based Volatility Forecasting of Agricultural Commodity Prices: Empirical Evidence From India”. Journal Big Data, 12: 85.
23. Marshall, R. C. (1991) “A State Space Forecasting Approach to Commodity Futures Trading”, The University of Arizona, USA.
24. Mergner, S. (2009) “Applications Of State Space Model in Finance”, PhD thesis, Universitätsverlag Gőttingen.
25. Nelson, D. B. and Cao, C. Q. (1992) “Inequality Constraints in the Univariate GARCH Model”, Journal of Business and Economic Statistics, 10(2): 229-235.
26. Neslihanoglu, S. (2014) “Validating And Extending the Two-Moment Capital Asset Pricing Model for Financial Time Series”, Doctoral dissertation, University of Glasgow, UK.
27. Neslihanoğlu, S. and Aksoy, T (2020) “BİST’teki Ulaştırma Sektörü Firmalarının Verilerinin Modellenmesi Ve Gelecek Tahmini İçin Doğrusal Piyasa Modeli Yeterli Mi?”, Journal of Management and Economics Research, 18(4): 54-72.
28. Neslihanoğlu, S. and Paker, M. (2021) “Beta Risklerinin Modellenmesi ve Tahmini: Türkiye’deki Döviz Portföyü Örneği”, Çankırı Karatekin Üniversitesi İktisadi ve İdari Bilimler Fakültesi Dergisi, 11(2): 467-491.
29. R Core Team (2018) “R: A Language and Environment for Statistical Computing”, R Foundation for Statistical Computing, Vienna, Austria.
30. Shokoohi, Z. and Tarazkar, M. H. (2022) “Meat Price Bubble in Iran: An Empirical Evidence from State‐Space Model”, Journal of Agricultural Economics and Development, 36(2): 157-167.
31. Sørensen, C. (2002) “Modeling Seasonality In Agricultural Commodity Futures”, Journal of Futures Markets, 22(5): 393–426.
32. Su, M., Nie, Y., Li, J., Yang, L., and Kim, W. (2024) “Futures Markets and the Baltic Dry Index: A Prediction Study based on Deep Learning”, Research in International Business and Finance, 71: 102447.
33. Swarup, S. and Kushwaha, G. S. (2022) “An Approach for Forecasting the Onion Price Volatility in Indian Wholesale Markets Using Hybrid GARCH-LSTM Deep Learning Models”, Research Square.
34. Yahoo Finance (2025) https://finance.yahoo.com, Accessed on: 31 December 2025.
35. Zhang, T. and Tang, Z. (2024) “Agricultural Commodity Futures Prices Prediction based on a New Hybrid Forecasting Model Combining Quadratic Decomposition Technology and LSTM Model” Frontiers Sustainable Food Systems, 8: 1334098.