SavedAdd your journal

Journals / Uluslararası Yönetim İktisat ve İşletme Dergisi / 2026 / Cilt: 22 Sayı: 1

A MACHINE LEARNING APPROACH BASED ON THE HERFINDAHL-HIRSCHMAN INDEX FOR DETERMINING THE ENERGY SUPPLY SECURITY LEVELS OF COUNTRIES

ÜLKELERİN ENERJİ ARZ GÜVENLİĞİ DÜZEYLERİNİN BELİRLENMESİ İÇİN HERFINDAHL-HIRSCHMAN ENDEKSİ TABANLI MAKİNE ÖĞRENMESİ YAKLAŞIMI

Serkan Metin(TURGUT ÖZAL ÜNİVERSİTESİ)0000-0003-1765-7474
Pages
83–103
Publication Date
2026-03-26
🏛️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 results show that Spain, with the lowest HHI value (0.2), has the highest level of energy supply security, while Paraguay, with the highest HHI value (1), has the lowest.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:The security of energy supply constitutes one of the most critical national security concerns for countries.
📊
Key Findings & Data:Reliance on a single energy source and supplier poses significant threats to a nation’s future, so governments must diversify the resources used in energy production.
💡
Conclusion & Impact:The results show that Spain, with the lowest HHI value (0.2), has the highest level of energy supply security, while Paraguay, with the highest HHI value (1), has the lowest.
🔬Design:Araştırma Makalesi
📍Scope:2000 Verileri
⚙️Variables:Enerji Arz Güvenliği · Herfindahl-Hirschman Endeksi · Makine Öğrenmesi

Abstract

The security of energy supply constitutes one of the most critical national security concerns for countries. Reliance on a single energy source and supplier poses significant threats to a nation’s future, so governments must diversify the resources used in energy production. The objective of this study is to assess countries’ status with respect to energy supply security by measuring the diversity of their energy sources. To this end, the Herfindahl–Hirschman Index (HHI) and a suite of machine‑learning methods were employed to determine countries’ levels of energy supply security. High HHI values indicate that energy supply security is at risk and that a country is externally dependent on its energy resources. A dataset covering 77 countries from 2000 to 2023 was analysed to evaluate their energy supply security levels. The results show that Spain, with the lowest HHI value (0.2), has the highest level of energy supply security, while Paraguay, with the highest HHI value (1), has the lowest. As a secondary approach, the results from the HHI‑based classification were reclassified using machine‑learning techniques, including K‑Nearest Neighbours (KNN), Random Forest, Logistic Regression and Support Vector Machines (SVM). Among these methods, Random Forest achieved the best performance, with an accuracy rate of 94 %.

Özet

Enerji arz güvenliği ülkeler açısından en önemli milli güvenlik sorunlarından biridir. Tek bir enerji kaynağına ve tedarikçiye bağımlı olmak ülkelerin geleceği açısından büyük tehditler oluşturmaktadır. Bunun için ülkeler enerji üretiminde kullanacağı kaynakları çeşitlendirmek zorundadırlar. Çalışmanın amacı, enerji kaynaklarının çeşitliliğini ölçerek ülkelerin enerji arz güvenliği açısından hangi durumda olduklarını değerlendirmektir. Bu çalışmada, ülkelerin enerji arz güvenliği düzeylerini belirlemek için Herfindahl-Hirschman Endeksi (HHI) ve makine öğrenmesi yöntemleri kullanılmıştır. HHI değerlerinin yüksek olması enerji arz güvenliğinin riskte olduğunu ve enerji kaynakları açısından dışa bağımlılığın olduğunu göstermektedir. Çalışmada, 2000-2023 yılları arasındaki 77 ülkeye ait veri seti analiz edilerek enerji arz güvenliği seviyeleri değerlendirilmiştir. Elde edilen sonuçlar, İspanya’nın en düşük HHI değeri (0,2) ile en yüksek enerji arz güvenliğine Paraguay’ın ise en yüksek HHI değeri (1) ile en düşük enerji arz güvenliğine sahip olduğunu göstermiştir. İkinci yöntem olarak da, makine öğrenmesi yöntemlerinden K En Yakın Komşu (KNN), Rastgele Orman (Random Forest), Lojistik Regresyon ve Destek Vektör Makineleri (SVM) yöntemleri ile HHI sınıflandırmadan elde edilen sonuçlar ile yeniden sınıflandırma işlemleri yapılmıştır. Random Forest, %94 doğruluk oranıyla en başarılı yöntem olmuştur.

🔖

Cite This Article

Metin, S. (2026). A MACHINE LEARNING APPROACH BASED ON THE HERFINDAHL-HIRSCHMAN INDEX FOR DETERMINING THE ENERGY SUPPLY SECURITY LEVELS OF COUNTRIES. Uluslararası Yönetim İktisat ve İşletme Dergisi, Cilt: 22 Sayı: 1, 83–103. https://doi.org/10.17130/ijmeb.1617073

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (35)

  1. Abbas, Q., & Alqama, K., (2020). Energy security: A national security paradigm shift for US in post 9/11 epoch. Review of Economics and Development Studies, 6(2), 381-390. https://doi.org/10.47067/reads.v6i2.216
  2. Abouemara, K., Shahbaz, M., Mckay,G., & Al-Ansari, T. (2024). The review of power generation from integrated biomass gasification and solid oxide fuel cells: Current status and future directions. Fuel, 360, 1-20. https://doi.org/10.1016/j.fuel.2023.130511
  3. APERC. 2007. A quest for energy security in the 21st century, ISBN 978-4-931482-35-7
  4. Aslani, A., Helo, P., & Naaranoja, M. (2014). Role of renewable energy policies in energy dependency in Finland: System dynamics approach. Appl. Energy, 113, 758–765. https://doi.org/10.1016/j.apenergy.2013.08.015
  5. Bazilian, M., Hobbs, B.F., Blyth, W., MacGill, I., & Howells, M. (2011). Interactions between energy security and climate change: A focus on developing countries. Energy Policy. https://doi.org/10.1016/j.enpol.2011.04.003
  6. Blyth, W., & Lefevre, N. (2004). Energy security and climate change policy interactions. IEA, Paris.
  7. Bronfman, N.C., Jimenez, R.B., Arevalo, P.C. & Cifuentes, L.A. (2012). Understanding social acceptance of electricity generation sources. Energy Policy, 46, 246–252. http://doi.org/10.1016/j.enpol.2012.03.057
  8. Bucciarelli, P., Hache E., & Mignon, V. (2024). Evaluating criticality of strategic metals: Are the Herfindahl–Hirschman index and usual concentration thresholds still relevant?. Hal-04452384, 1-49.
  9. Cabalu, H. (2010). Indicators of security of natural gas supply in Asia. Energy Policy, 38, 218–225. http://doi.org/10.1016/j.enpol.2009.09.008
  10. Carpio, L.G.T., & Guimaraes, F.A.C. (2024). Regional diversification of hydro, wind, and solar generation potential: A mean-variance model to stabilize power fluctuations in the Brazilian integrated electrical energy transmission and distribution system. Renewable Energy, 235(21266), 1-12. https://doi.org/10.1016/j.renene.2024.121266
  11. Chalvatzis, K.J., & Ioannidis, A. (2017). Energy supply security in the EU: Benchmarking diversity and dependence of primary energy. Applied Energy, 207, 465–476. http://doi.org/10.1016/j.apenergy.2017.07.010
  12. Chomboon, K., Chujai, P., Teerarassamee, P., Kerdprasop, K., & Kerdprasop, N. (2015). An empirical study of distance metrics for k-nearest neighbor algorithm. Proceedings of the 3rd International Conference on Industrial Application Engineering, 280-285. https://doi.org/10.12792/iciae2015.051 280
  13. Chuang, M.C., & Ma, H.W. (2013). Energy security and improvements in the function of diversity indices—Taiwan energy supply structure case study. Renewable and Sustainable Energy Reviews, 24, 9–20. http://doi.org/10.1016/j.rser.2013.03.021
  14. Costantini, V., Gracceva, F., Markandya, A., & Vicini, G. (2007). Security of energy supply: Comparing scenarios from a European perspective. Energy Policy, 35, 210–226. http://doi.org/10.1016/j.enpol.2005.11.002
  15. Dagar, V., Dagher, L., Rao, A., Doytch, N., & Kagzi, M. (2024). Economic policy uncertainty: Global energy security with diversification. Economic Analysis and Policy, 82, 248–263. https://doi.org/10.1016/j.eap.2024.03.008
  16. Dioşan, L., Rogozan, A. & Pecuchet, JP. (2012). Improving classification performance of support vector machine by genetically optimising kernel shape and hyper-parameters. Appl Intell 36, 280–294. https://doi.org/10.1007/s10489-010-0260-1
  17. Georgiou, P.N, Mavrotas, G., & Diakoulaki, D. (2011). The effect of islands interconnection to the mainland system on the development of renewable energy sources in the Greek power sector. Renewable and Sustainable Energy Reviews, 15(6), 2607–2620. https://doi.org/10.1016/j.rser.2011.03.007
  18. Grubb, M., Butler, L., & Twomey P. (2006). Diversity and security in UK electricity generation: The influence of low-carbon objectives. Energy Policy, 34, 4050–4062. http://doi.org/10.1016/j.enpol.2005.09.004
  19. Kafi, F., Amrouci, H., & Necira, B. (2024). Energy security and diversification of energy resources are imperative for building a new model of development in Algeria. Remittances Review, 9(1), 122-139. doi: https://doi.org/10.33182/rr.v9i1.010
  20. Kaldellis, J.K., & Zafirakis, D. (2007). Present situation and future prospects of electricity generation in aegean Archipelago Islands. Energy Policy, 35, 4623–4639. https://doi.org/10.1016/j.enpol.2007.04.004
  21. Khan, T. A., Sadiq, R., Shahid, Z., Alam, M. M., & Mohd Su’ud, M. B. (2024). Sentiment analysis using support vector machine and random forest. Journal of Informatics and Web Engineering, 3(1), 67–75. https://doi.org/10.33093/jiwe.2024.3.1.5
  22. Kruyt, B., Vuuren, D.P., Vries, H.J.M., & Groenenberg, H. (2009). Indicators for energy security. energy policy, 37, 2166–2181. https://doi.org/10.1016/j.enpol.2009.02.006
  23. Lambert, L.A., Tayah, J., Lee-Schmid, C., Abdalla, M., Abdallah, I., Ali, A.H.M, Esmail, S., & Ahmed, W. (2022). The EU’s natural gas cold war and diversification challenges. Energy Strategy Rev, 43, 1-9. https://doi.org/10.1016/j.esr.2022.100934
  24. Lekavicius, V., Balsiunaite, R., Bobinaite, V., Konstantinaviciute, I, Rimkunaite, K., Streimikiene, D., & Tarvydas, D. (2024). The diversification of energy resources and equipment imports in the European Union. Energy, 307(132595), 1-14. https://doi.org/10.1016/j.energy.2024.132595
  25. Lu, C., Qiao, J., & Chang, J. (2017). Herfindahl–Hirschman index based performance analysis on the convergence development. Cluster Comput, 20, 21–129. https://doi.org/10.1007/s10586-017-0737-3
  26. Noviyanti, C.N., & Alamsyah. (2024). Early detection of diabetes using random forest algorithm. Journal of Information System Exploration and Research, 2(1), 41-48. doi: https://doi.org/10.52465/joiser.v2i1.245
  27. Oikonomou, E.K., Kilias, V., Goumas, A., Rigopoulos, A., Karakatsani, E., Damasiotis, M., Papastefanakis, D., & Marini, N. (2009). Renewable energy sources (RES) projects and their barriers on a regional scale: The case study of wind parks in the Dodecanese Islands, Greece. Energy Policy, 37, 4874–4883. http://doi.org/10.1016/j.enpol.2009.06.050
  28. Prabhat, A. & Khullar, V. (2017). Sentiment classification on big data using naive bayes and logistic regression. International Conference on Computer Communication and Informatics (ICCCI -2017), 1-5. http://doi.org/10.1109/ICCCI.2017.8117734
  29. Rachmatullah, C., Aye, L., & Fuller, R.J. (2007). Scenario planning for the electricity generation in Indonesia. Energy Policy, 35, 2352–2359. http://doi.org/10.1016/j.enpol.2006.08.015
  30. Rivera, N. M., Ruiz-Tagle, J. C., & Spiller, E. (2024). The health benefits of solar power generation: Evidence from Chile. Journal of Environmental Economics and Management, 126(102999), 1-20. https://doi.org/10.1016/j.jeem.2024.102999
  31. Rój J. (2016). Competition measurement of hospitals in Poland: The Herfındahl-Hirschman index approach. Ekonomika, 95(1), 166- 181.
  32. Strantzalia, E., Aravossisa, K. & Livanos, G.A. (2017). Evaluation of future sustainable electricity generation alternatives: The case of a Greek island. Renewable and Sustainable Energy Reviews, 76, 775–787. http://doi.org/10.1016/j.rser.2017.03.085
  33. Susilo, Y.O., & Axhausen, K.W. (2014). Repetitions in individual daily activity–travel–location patterns: A study using the Herfindahl–Hirschman Index. Transportation, 41, 995–1011. http://doi.org/10.1007/s11116-014-9519-4
  34. Teker, S., Azkeskin, S. A. & Aladağ, Z. (2024). Enerji sürdürülebilirliğinin çok kriterli karar verme yöntemleri ile ölçülmesi ve Copeland yöntemi ile bütünleştirilmesi: OECD ülkeleri üzerine bir çalışma. Uluslararası Yönetim İktisat ve İşletme Dergisi, 20(4), 871-895. http://doi.org/10.17130/ijmeb.1440773
  35. Triguero-Ruiz, F., Avila-Cano, A., & Aranda, F.T. (2023). Measuring the diversification of energy sources: The energy mix. Renewable Energy, 216 (119096), 1-8. https://doi.org/10.1016/j.renene.2023.119096