SavedAdd your journal

Journals / Uşak Üniversitesi Uygulamalı Bilimler Fakültesi Dergisi / 2026 / Cilt: 6 Sayı: 1

PREDICTING NOMINAL GROSS DOMESTIC PRODUCT LEVELS IN TÜRKIYE USING SUPPORT VECTOR REGRESSION

Destek Vektör Regresyonu Kullanarak Türkiye’deki Nominal Gayri Safi Yurt İçi Hasila Seviyelerinin Tahmini

Enes Filiz(BALIKESİR ÜNİVERSİTESİ)0000-0002-8006-9467
Pages
38–52
Publication Date
2026-06-29
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)

The findings indicate that the SVR-Poly model achieves a Direction Accuracy (Dac) of 82.95% with the raw dataset, which improves to 89.10% when focusing on six core variables: taxes on products, gross operating surplus, consumption of fixed capital, services, net operating surplus, and other service activities.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:Gross Domestic Product (GDP) serves as one of the most fundamental indicators for evaluating the economic performance and growth potential of a nation.
📊
Key Findings & Data:In an increasingly complex global financial landscape, accurately predicting these figures is crucial for strategic planning and policy development.
💡
Conclusion & Impact:The findings indicate that the SVR-Poly model achieves a Direction Accuracy (Dac) of 82.95% with the raw dataset, which improves to 89.10% when focusing on six core variables: taxes on products, gross operating surplus, consumption of fixed capital, services, net operating surplus, and other service activities.
🔬Design:Modeling & Simulation
📍Scope:2024 Verileri
⚙️Variables:Gayri Safi Yurt İçi Hasıla · Destek Vektör Regresyonu · Tahmin

Abstract

Gross Domestic Product (GDP) serves as one of the most fundamental indicators for evaluating the economic performance and growth potential of a nation. In an increasingly complex global financial landscape, accurately predicting these figures is crucial for strategic planning and policy development. This study focuses on predicting Türkiye's Nominal GDP levels using the Support Vector Regression (SVR) algorithm with a polynomial kernel, while employing the Correlation Attribute method for feature selection. The analysis utilizes a comprehensive dataset covering the period between 1995: Q1 and 2024: Q4 for model training, targeting the four quarters of 2025 for predicting. The findings indicate that the SVR-Poly model achieves a Direction Accuracy (Dac) of 82.95% with the raw dataset, which improves to 89.10% when focusing on six core variables: taxes on products, gross operating surplus, consumption of fixed capital, services, net operating surplus, and other service activities. These results suggest that Nominal GDP in Türkiye is predominantly driven by tax dynamics and the service sector. The proposed framework provides a practical tool for researchers and decision-makers to understand the country's economic trajectory with higher precision.

Özet

Gayri Safi Yurt İçi Hasıla (GSYİH), bir ülkenin ekonomik performansını ve büyüme potansiyelini değerlendirmek için kullanılan en temel göstergelerden biridir. Küresel finansal yapının giderek karmaşıklaştığı günümüzde, bu rakamların doğru tahmin edilmesi stratejik planlama ve politika geliştirme süreçleri açısından kritik bir önem taşımaktadır. Bu çalışma, değişken seçiminde Correlation Attribute yönteminden yararlanırken, Türkiye’nin Nominal GSYİH seviyelerini tahmin etmek için polinom çekirdekli Destek Vektör Regresyonu (SVR) algoritmasını kullanmaktadır. Analiz kapsamında, 1995: Ç1 ile 2024: Ç4 arasındaki dönem model eğitimi için ayrılırken, 2025 yılının dört çeyreği tahmin hedefi olarak belirlenmektedir. Elde edilen bulgular, SVR-Poly modelinin ham veri setiyle %82,95 olan Yönsel Doğruluk (Dac) oranının; ürün üzerindeki vergiler, brüt işletme artığı, sabit sermaye tüketimi, hizmetler, net işletme artığı ve diğer hizmet faaliyetlerinden oluşan altı temel değişkene odaklanıldığında %89,10’a yükseldiğini göstermektedir. Bu sonuçlar, Türkiye’deki Nominal GSYİH’nin ağırlıklı olarak vergi dinamikleri ve hizmet sektörü tarafından şekillendiğine işaret etmektedir. Sunulan çerçeve, araştırmacılar ve karar vericiler için ülkenin ekonomik seyrini daha yüksek isabetle anlama konusunda pratik bir araç sunmaktadır.

🔖

Cite This Article

Filiz, E. (2026). PREDICTING NOMINAL GROSS DOMESTIC PRODUCT LEVELS IN TÜRKIYE USING SUPPORT VECTOR REGRESSION. Uşak Üniversitesi Uygulamalı Bilimler Fakültesi Dergisi, Cilt: 6 Sayı: 1, 38–52. https://ajindex.com/articles/1623668

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (37)

  1. Abanda, F. H., Ng’ombe, A., Keivani, R. and Tah, J. H. M. (2012). The link between renewable energy production and gross domestic product in Africa: A comparative study between 1980 and 2008. Renewable and Sustainable Energy Reviews, 16(4), 2147-2153. doi: https://doi.org/10.1016/j.rser.2012.01.005.
  2. Akbulut, H. (2022). Forecasting inflation in Turkey: A comparison of time-series and machine learning models. Economic Journal of Emerging Markets, 55-71. doi: https://doi.org/10.20885/ejem.vol14.iss1.art5.
  3. Arnold, J. M., Brys, B., Heady, C., Johansson, Å., Schwellnus, C. and Vartia, L. (2011). Tax policy for economic recovery and growth. The Economic Journal, 121(550), F59-F80. doi: https://doi.org/10.1111/j.1468-0297.2010.02415.x.
  4. Barnett, W. A., Chauvet, M. and Leiva-Leon, D. (2016). Real-time nowcasting of nominal GDP with structural breaks. Journal of Econometrics, 191(2), 312-324. doi: https://doi.org/10.1016/j.jeconom.2015.12.004.
  5. Beckworth, D. and Horan, P. J. (2024). A two-for-one deal: Targeting nominal GDP to create a supply-shock robust inflation target. Journal of Policy Modeling, 46(6), 1071-1089. doi: https://doi.org/10.1016/j.jpolmod.2024.05.014.
  6. Bodas-Sagi, D. J. and Labeaga, J. M. (2015, April). Predicting Energy Demand in Spain and Compliance with the Greenhouse Gas Emissions Agreements. In International Conference on Dynamics, Games and Science (pp. 107-126). Cham: Springer International Publishing.
  7. Chen, H. (2021). On the welfare implications of nominal GDP targeting. Journal of Macroeconomics, 69, 103336. doi: https://doi.org/10.1016/j.jmacro.2021.103336.
  8. Central Bank of the Republic of Türkiye Web Page. (2025). Türkiye Gross Domestıc Product Levels. Access date: 16.02.2026. https://evds2.tcmb.gov.tr/index.php?/evds/serieMarket/#collapse_2.
  9. Ecer, F. (2013). Comparing the bank failure prediction performance of neural networks and support vector machines: The Turkish case. Economic research-Ekonomska istraživanja, 26(3), 81-98. doi: https://doi.org/10.1080/1331677X.2013.11517623.
  10. Emmoh, P. U., Eke, C. I. and Moses, T. (2025). A feature selection and scoring scheme for dimensionality reduction in a machine learning task. Journal of the Nigerian Society of Physical Sciences, 2273-2273. doi: https://doi.org/10.46481/jnsps.2025.2273.
  11. England, R. W. (1998). Measurement of social well-being: alternatives to gross domestic product. Ecological Economics, 25(1), 89-103. doi: https://doi.org/10.1016/S0921-8009(97)00098-0.
  12. Fackler, J. S. and McMillin, W. D. (2020). Nominal GDP versus price level targeting: An empirical evaluation. Journal of Economics and Business, 109, 105890. doi: https://doi.org/10.1016/j.jeconbus.2019.105890.
  13. Filiz, E. and Öz, E. (2019). Finding the Best Algorithms and Effective Factors in Classification of Turkish Science Student Success. Journal of Baltic Science Education, 18(2), 239-253.
  14. Filiz, E., Akogul, S. and Karaboğa, H. A. (2021). Büyük dünya endeksleri kullanılarak BIST-100 endeksi değişim yönünün makine öğrenmesi algoritmaları ile sınıflandırılması. Bitlis Eren Üniversitesi Fen Bilimleri Dergisi, 10(2), 432-441. doi: https://doi.org/10.17798/bitlisfen.889007.
  15. Garín, J., Lester, R. and Sims, E. (2016). On the desirability of nominal GDP targeting. Journal of Economic Dynamics and Control, 69, 21-44. doi: https://doi.org/10.1016/j.jedc.2016.05.004.
  16. Gogas, P., Papadimitriou, T.and Sofianos, E. (2019). Money neutrality, monetary aggregates and machine learning. Algorithms, 12(7), 137. doi: https://doi.org/10.3390/a12070137.
  17. Gollin, D. (2002). Getting income shares right. Journal of political Economy, 110(2), 458-474. doi: https://doi.org/10.1086/338747.
  18. Hu, Z., Yang, J., Wang, S. and Zhong, Z. (2016, November). Regional economic growth forecasting based on partial least square, support vector machine and prosperity index method. In 2016 31st Youth Academic Annual Conference of Chinese Association of Automation (YAC) (pp. 454-458). IEEE.
  19. Jiang, F., Meng, W. and Meng, X. (2009, April). Selectivity estimation for exclusive query translation in deep web data integration. In International conference on database systems for advanced applications (pp. 595-600). Berlin, Heidelberg: Springer Berlin Heidelberg.
  20. Kavaklioglu, K. (2011). Modeling and prediction of Turkey’s electricity consumption using Support Vector Regression. Applied Energy, 88(1), 368-375. doi: https://doi.org/10.1016/j.apenergy.2010.07.021.
  21. Kouziokas, G. N. (2020). A new W-SVM kernel combining PSO-neural network transformed vector and Bayesian optimized SVM in GDP forecasting. Engineering Applications of Artificial Intelligence, 92, 103650. doi: https://doi.org/10.1016/j.engappai.2020.103650.
  22. Kumar, S.and Muhuri, P. K. (2019). A novel GDP prediction technique based on transfer learning using CO2 emission dataset. Applied Energy, 253, 113476. doi: https://doi.org/10.1016/j.apenergy.2019.113476.
  23. Kutasi, G. and Marton, Á. (2024). The optimal tax structure from GDP-growth perspective. Revista Finanzas y Política Económica, 16(1), 121-143.
  24. Lai, P. and Zhu, T. (2022). Deflating China's nominal GDP: 2004–2018. China Economic Review, 71, 101709. doi: https://doi.org/10.1016/j.chieco.2021.101709.
  25. Lee, K. S. and Werner, R. A. (2018). Reconsidering monetary policy: An empirical examination of the relationship between interest rates and nominal GDP growth in the US, UK, Germany and Japan. Ecological Economics, 146, 26-34. doi: https://doi.org/10.1016/j.ecolecon.2017.08.013.
  26. Lyeonov, S., Pimonenko, T., Bilan, Y., Štreimikienė, D.and Mentel, G. (2019). Assessment of green investments’ impact on sustainable development: Linking gross domestic product per capita, greenhouse gas emissions and renewable energy. Energies, 12(20), 3891. doi: https://doi.org/10.3390/en12203891.
  27. Nguvava, H. E. and Bandile, L. E. (2025). The role of value added tax revenue on gross domestic product (GDP) in Tanzania. East African Journal of Business and Economics, 8(1), 85-95. doi: https://dx.doi.org/10.4314/ngjsd.v16i1.1.
  28. Ozden, E. and Guleryuz, D. (2022). Optimized machine learning algorithms for investigating the relationship between economic development and human capital. Computational Economics, 60(1), 347-373. doi: https://doi.org/10.1007/s10614-021-10194-7.
  29. Saiti, D. and Trenovski, B. (2023). Reconsidering Monetary Policy: Examination Of the Relationship Between Interest Rate and Nominal Gdp Growth in North Macedonia. Economic Vision International Scientific Journal in Economics, Finance, Business, Marketing, Management and Tourism, 10(19-20), 71-83.
  30. Saidi, R., Bouaguel, W. and Essoussi, N. (2018). Hybrid feature selection method based on the genetic algorithm and pearson correlation coefficient. In Machine learning paradigms: theory and application (pp. 3-24). Cham: Springer International Publishing.
  31. Sheedy, K. D. (2014). Debt and incomplete financial markets: A case for nominal GDP targeting. Brookings Papers on Economic Activity, 2014(1), 301-373. doi: https://dx.doi.org/10.1353/eca.2014.0005.
  32. Shevade, S. K., Keerthi, S. S., Bhattacharyya, C. and Murthy, K. R. K. (2000). Improvements to the SMO algorithm for SVM regression. IEEE transactions on neural networks, 11(5), 1188-1193. doi: 10.1109/72.870050.
  33. Smola, A. J. and Schölkopf, B. (2004). A tutorial on support vector regression. Statistics and Computing, 14(3), 199-222. doi: https://doi.org/10.1023/B:STCO.0000035301.49549.88.
  34. Tuncsiper, C. (2023). A deep learning network for modelling the relationship of the real gdp, co2 emission and renewable energy consumption for Turkiye. Cognizance Journal, 3(1), 35-46. doi: https://doi.org/ 10.47760/cognizance.2023.v03i01.003.
  35. Ülker, E. D. and Ülker, S. (2019, November). Unemployment rate and GDP prediction using support vector regression. In Proceedings of the 1st International Conference on Advanced Information Science and System (pp. 1-5).
  36. Wolff, E. N. (2003). What's behind the rise in profitability in the US in the 1980s and 1990s?. Cambridge Journal of Economics, 27(4), 479-499. doi: https://doi.org/10.1093/cje/27.4.479.
  37. Zhang, Q. and Bian, Y. (2025). Understanding Machine Learning-based Methods in Macroeconomic Forecasting: Tracking Chinese GDP Growth Rate. Computational Economics, 1-53. doi: https://doi.org/10.1007/s10614-025-11115-8.