SavedAdd your journal

Journals / Ege Akademik Bakış / 2018 / Cilt: 18 - Sayı: 4

Forecasting the Direction of Agricultural Commodity Price Index through ANN, SVM and Decision Tree: Evidence from Raisin

YSA, DVM ve Karar Ağacı ile Tarımsal Emtiaların Fiyat Endekslerinin Tahminlenmesi: Kuru Üzüm Örneği

Erçin Güdücü
Burcu Akın
İkbal Ece Dizbay
Şevkinaz Gümüşoğlu
Pages
579–588
Publication Date
2022-10-12
DOI
—
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

Experimental results showed thataccuracy performance of SVM method wasfound significantly better than ANN method anddecision tree.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:To be able to make appropriate actionsduring buying, selling or holding decisions,economic actors need accurate commodityprice forecasts.
📊
Key Findings & Data:Lastly, which method hasthe best prediction performance; ArtificialNeural Networks (ANN), Decision Tree orSupport Vector Machine (SVM)?
💡
Conclusion & Impact:Experimental results showed thataccuracy performance of SVM method wasfound significantly better than ANN method anddecision tree.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:Domain Parameters

Abstract

To be able to make appropriate actionsduring buying, selling or holding decisions,economic actors need accurate commodityprice forecasts. This study focuses on forecastingraisin price by using predetermined volatilevariables. Therefore, we seek for answers ofthree main questions. Do the social & politicalissues effect raisin price in countries thathave internal disturbance? By using volatilevariables, can we represent or predict priceindex thoroughly? Lastly, which method hasthe best prediction performance; ArtificialNeural Networks (ANN), Decision Tree orSupport Vector Machine (SVM)? In accordancewith these purposes, ANN, decision tree andSVM methods are implemented for proposedmodel and their prediction performances arecompared. Experimental results showed thataccuracy performance of SVM method wasfound significantly better than ANN method anddecision tree.

Özet

Emtia fiyat endekslerinin başarılı bir şekilde tahminlenmesi ekonomik aktörlere doğru alım satım kararları verebilmeleri için fayda sağlamaktadır. Türkiye’deki ticaret borsalarında işlem gören tarımsal ürünlerden biri olan kuru üzüm fiyatlarının oynak değişkenler kullanılarak tahminlenmesinin incelendiği çalışmada üç temel soru üzerinde durulmuştur. İç karışıklığın yüksek olduğu ülkelerde sosyal ve politik olaylar kuru üzüm fiyatlarını etkiler mi? Oynaklığı yüksek olan değişkenler kullanılarak kuru üzüm fiyat endeksleri tahminlenebilir mi? Son olarak, bu tip bir çalışmada Yapay Sinir Ağları (YSA), Karar Ağacı ve Destek Vektör Makineleri (DVM) yöntemlerinden hangisinin tahmin performansı daha yüksektir? Bu amaçla oluşturulan tahmin modeline YSA, KA ve DVM yöntemleri uygulanmış ve yöntemlerin tahmin performansları karşılaştırılmıştır. Uygulama sonuçları, oynak değişkenler ile sosyal ve politik olayların kuru üzüm fiyatlarının tahminlenmesinde kullanılabileceğini ve ilgili modelde DVM yönteminin en yüksek doğruluk oranını verdiğini göstermiştir.

🔖

Cite This Article

Güdücü, E., Akın, B., Dizbay, İ. E., Gümüşoğlu, Ş. (2022). Forecasting the Direction of Agricultural Commodity Price Index through ANN, SVM and Decision Tree: Evidence from Raisin. Ege Akademik Bakış, Cilt: 18 - Sayı: 4, 579–588. https://ajindex.com/articles/495177

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (10)

  1. Ahmed, S. (2008). Aggregate economic variables and stock markets in India. International Research Journal of Finance and Economics, 14, 141-164.
  2. Azadeh, A., Moghaddam, M., & Khakzad, M. (2012). A flexible neural network-fuzzy mathematical programming algorithm for improvement of oil price estimation and forecasting. Comput. Ind. Eng. 62(2): 421–430.
  3. Baffes, J., & Haniotis, T. (2016). What explains agricultural price movements? Journal of Agricultural Economics, 67(3), 706-721.
  4. Chen, A.-S., Leung, M. T., & Daouk, H. (2003). Application of neural networks to an emerging financial market: forecasting and trading the Taiwan Stock Index. Computers & Operations Research, 30(6), 901-924.
  5. Chen, Y. C., Rogoff, K., & Rossi, B. (2010). Predicting agri-commodity prices: An asset pricing approach. SSRN. Cortes, C., & Vapnik, V. (1995). Support-vector networks. Machine learning, 20(3), 273-297.
  6. Dean, J. (2014). Big data, data mining, and machine learning: value creation for business leaders and practitioners. New Jersey: John Wiley & Sons. Computational intelligence methods for rule-based data understanding. Proceedings of the IEEE, 92(5), 771-805.
  7. Duch, W., Setiono, R., & Zurad, J. (2004). Computational intelligence methods for rule-based data understanding. Proceedings of the IEEE, 92(5), 771- 805. Gargano, A., & Timmermann, A. (2014). Forecasting commodity price indexes using macroeconomic and financial predictors. International Journal of Forecasting, 30(3), 825-843.
  8. Groen, J., & Pesenti, P. A. (2011). Commodity prices, commodity currencies, and global economic developments. In T. Ito, & A. Rose, Commodity prices and markets, East Asia Seminar on Economics (Vol. 20, pp. 15–42 ). Chicago: University of Chicago. Haidar, I., & Wolff, R. (2009). Forecasting crude oil price. Retrieved from http://www.usaee.org/usaee2011/ submissions/ OnlineProceedings/Forecasting%20 Crude%20Oil%20Price%20%28Revisited%29.pdf. Hong, H., & Yogo, M. (2012). What does futures market interest tell us about the macroeconomy and asset prices? Journal of Financial Economics, 105(3), 473–490.
  9. Hu, J. W.-S., Hu, Y.-C., & Lin, R. R.-W. (2012). Applying neural networks to prices prediction of crude oil futures. Mathematical Problems in Engineering. Jammazi, R., & Aloui, C. (2012). Crude oil price forecasting: experimental evidence from wavelet decomposition and neural network modeling 34: 828–841. Energy Econ., 34(3), 828-841.
  10. Jha, G. K., & Sinha, K. (2014). Time-delay neural networks for time seri