DETERMINING THE PREDICTION OF THE EXPORT UNIT VALUE INDEX USING THE M5 RULES MACHINE LEARNING ALGORITHM

Enes Filiz

TR EN

İhracat Birim Değer Endeksinin M5 Kural Tabanlı Makine Öğrenmesi Algoritması Ile Tahmininin Belirlenmesi

Öz

Dünya’daki kaynakların gün geçtikçe azalması ülkeler açısından ihracatın önemini daha da arttırmaktadır. Ülkelerin yaşanacak ya da karşılacak her türlü sorun için tedbirli olması gerekmektedir. Bunun için ihracata önem vermelidir. İhracat konusunda olabildiğince kendi ayaklarının üzerinde durabilmesi ülkenin gelişmişlik düzeyini göstermektedir. İhracatın gelişmesi ile hem ekonomik hem de refah açısından problemler azalmaktadır. Bu çalışmada, Türkiye’nin ihracat birim değer endeksinin tahmininin belirlenmesi amaçlanmıştır. Türkiye Cumhuriyeti Merkez Bankası’nın Nisan 2013 ile Aralık 2024 arası aylık verileri çalışmada kullanılacaktır. Türkiye’nin ihracat birim değer endeksinin tahmininin belirlenmesi için M5 kural tabanlı makine öğrenmesi algoritmasından yararlanılacaktır. Türkiye’nin ihracat birim değer endeksinin tahminine etki eden değişkenlerin belirlenmesi için Korelasyon tabanlı (Cfs Subset) öznitelik seçim algoritması çalışmaya dahil edilmiştir. Weka program ile yapılan analizler sonucunda genel olarak hem tüm değişkenler ile hem de etkili değişkenler ile M5 kural tabanlı makine öğrenmesinin başarılı tahminler yaptığı belirlenmiştir. Ayrıca Türkiye’nin ihracat birim değer endeksinin tahminine etki eden değişkenler ‘Yatırım Malları (Ulaşım Araçları Hariç)’, ‘Ham Maddeler (Ara Mallar)’, ‘İşlenmemiş Sanayi Ham Maddeleri’, ‘Tüketim Malları’ ve ‘Gıda ve İçecek Bazlı İşlenmiş Tüketim Malları’ olarak bulunmuştur.

Anahtar Kelimeler

M5 kural tabanlı makine öğrenmesi algoritması, Tahminleme, Korelasyon tabanlı öznitelik seçim algoritması, İhracat birim değer endeksi

Destekleyen Kurum

Yok

Etik Beyan

Yazarlar, bu çalışmanın hazırlanması boyunca etik kurallara uyulduğunu beyan ederler. Herhangi bir ihlal tespit edilmesi durumunda, Akademik İzdüşüm Dergisinin hiçbir sorumluluğu yoktur ve tüm sorumluluk çalışmanın yazarlarına aittir.

Teşekkür

Yok

DETERMINING THE PREDICTION OF THE EXPORT UNIT VALUE INDEX USING THE M5 RULES MACHINE LEARNING ALGORITHM

Öz

The growing global resource scarcity is increasing the importance of exports for countries. Countries must be prepared for any potential problems that may occur. To this end, they must prioritize their export strategies. A country’s ability to be self-sufficient through exports demonstrates its level of development. As exports grow economic challenges decrease while national welfare improves. This study aims to predict Türkiye's export unit value index. Monthly data from April 2013 to December 2024 from the Central Bank of the Republic of Türkiye is used in the study. The M5 rules machine learning algorithm will be used to predict Türkiye's export unit value index. The correlation-based (Cfs Subset) feature selection algorithm was included to identify the effective variables the prediction of Türkiye's export unit value index. The results of the analysis with the Weka program demonstrate that M5 rules machine learning was successful in making predictions using both all variables and effective variables. Furthermore, the effective variables the prediction of Türkiye's export unit value index were found to be ‘Investment Goods (Excluding Transportation Vehicles)’, ‘Raw Materials (Intermediate Goods)’, ‘Unprocessed Industrial Raw Materials’, ‘Consumer Goods’, and ‘Food and Beverage-Based Processed Consumer Goods’.

Anahtar Kelimeler

M5 rules machine learning algorithm, Prediction, Correlation-based feature selection algorithm, Export unit value index

Destekleyen Kurum

No

Etik Beyan

The author declare that ethical rules were followed throughout the preparation of this study. In the event that any violation is detected, Journal of Academic Projection bears no responsibility, and all responsibility lies with the authors of the study.

Teşekkür

No

Kaynakça

Abdelsamiea, A. T., El-Aal, A., & Mohamed, F. (2025). Industrial exports and global carbon emissions: assessing the impact of the US and China using a decision tree algorithm. International Journal of Energy Economics and Policy, 15(6), 281-286.
Al Khaldy, M. (2024, July). Correlation-Based Feature Selection for Enhanced Arrhythmia Classification. In International Conference on Intelligent and Fuzzy Systems (pp. 355-364). Cham: Springer Nature. Switzerland. Athukorala, P. C., & Sen, K. (1998). Processed food exports from developing countries: patterns and determinants. Food Policy, 23(1), 41-54.
Augustine, M., & Runge, C. (2025). Impact of Money Supply on Export Price Index. Available at SSRN 5259451. http://dx.doi.org/10.2139/ssrn.5259451
Ayaz, Y., Kocamaz, A. F., & Karakoç, M. B. (2015). Modeling of compressive strength and UPV of high-volume mineral-admixtured concrete using rule-based M5 rule and tree model M5P classifiers. Construction and Building Materials, 94, 235-240.
Betai, N. V., & Chanda, R. (2020). Global value chain participation and intermediate export sophistication. IIM Bangalore Research Paper, (629). http://dx.doi.org/10.2139/ssrn.3724329
Bui, D. T., Bui, K. T. T., Minh, N. Q., Ha, N. V., Van Chinh, D., & Revhaug, I. (2017). A comparative asessment of multi-layer perceptron neural networks and M5-rules algorithm for modeling and forecasting of horizontal displacement of the Hoa Binh hydropower dam (Vietnam). In The international symposium on geo-spatial and mobile mapping technology (GMMT2016). Hanoi.
Buturac, G. (2009). Structural characteristics of exports and imports of Croatian manufacturing. Ekonomski pregled, 60(9-10), 432-457.
Central Bank of the Republic of Turkey Web Page. (2025). Türkiye Export Unit Value Index. Access date: 25.12.2025: https://evds2.tcmb.gov.tr/index.php?/evds/serieMarket/#collapse_2.
Chand, K. S. P., Prabakaran, N., Ramani, S., Rao, D. V., & Vemparala, S. (2020). Assessment analysis and performance prediction using M5 rules. International Journal of Recent Technology and Engineering, 8(4), 12945-12951.
Curtis, A., & McLellan, B. (2023). Framework for Assessment of the Economic Vulnerability of Energy-Resource-Exporting Countries. Resources, 12(2), 27.

Dridi, J., & Zieschang, K. (2004). Export and import price indices. IMF Staff Papers, 51(1), 157-194.
Dudziński, J., & Knap, R. (2022). Price volume and level of economic development as determinants of export value in countries and regions. Procedia Computer Science, 207, 3865-3874.
Duggal, H., & Singh, P. (2012). Comparative study of the performance of M5-Rules algorithm with different algorithms. Journal of Software Engineering and Applications, 5(4), 270-276.
Fast, D., Fleck, S. E., & Smith, D. A. (2022). Unit Value Indexes for Exports–New Developments Using Administrative Trade Data. Journal of Official Statistics, 38(1), 83-106.
Filiz, E. (2023). Evaluation of match results of five successful football clubs with ensemble learning algorithms. Research quarterly for exercise and sport, 94(3), 773-782.
Gulzar, Y., Oral, C., Kayakus, M., Erdogan, D., Unal, Z., Eksili, N., & Caylak, P. C. (2024). Predicting High Technology Exports of Countries for Sustainable Economic Growth by Using Machine Learning Techniques: The Case of Turkey. Sustainability, 16(13), 5601.
Hall, M. A. (1988). Correlation-based feature subset selection for machine learning. Thesis submitted in partial fulfilment of the requirements of the degree of Doctor of Philosophy at the University of Waikato.
Holmes, G., Hall, M., & Frank, E. (1999, December). Generating rule sets from model trees. In Australasian joint conference on artificial intelligence (pp. 1-12). Berlin, Heidelberg: Springer Berlin Heidelberg.
Jia, H., Adland, R., & Wang, Y. (2021). Global oil export destination prediction: a machine learning approach. The Energy Journal, 42(4), 111-130.
Jiang, G., Alvarado, R., Murshed, M., Tillaguango, B., Toledo, E., Méndez, P., & Isik, C. (2022). Effect of agricultural employment and export diversification index on environmental pollution: building the agenda towards sustainability. Sustainability, 14(2), 677.
Kang, K. (2009). The export price index with the effect of variety and an empirical analysis. Economic Modelling, 26(2), 385-391.
Karegowda, A. G., & Jayaram, M. A. (2009, March). Cascading GA & CFS for feature subset selection in medical data mining. In 2009 IEEE International Advance Computing Conference (pp. 1428-1431). IEEE.
Karim, S. R., Sarker, D., & Kabir, M. M. (2024). Analyzing the impact of temperature on PV module surface during electricity generation using machine learning models. Cleaner Energy Systems, 9, 100135.
Lian, W., Novta, N., Pugacheva, E., Timmer, Y., & Topalova, P. (2020). The price of capital goods: a driver of investment under threat. IMF Economic Review, 68(3), 509-549.
Lu, X., Peng, X., Liu, P., Deng, Y., Feng, B., & Liao, B. (2012, August). A novel feature selection method based on CFS in cancer recognition. In 2012 IEEE 6th International Conference on Systems Biology (ISB) (pp. 226-231). IEEE.
Mathur, V. C., & Vasisht, A. K. (1994). An Analysis of Fluctuations in Unit Values, Quantum and Export Values of Tea. Agricultural Economics Research Review, 7(1), 25-37.
Micocci, F., & Rungi, A. (2023). Predicting exporters with machine learning. World Trade Review, 22(5), 584-607.
Millenia, I. F., Zukhronah, E., & Sulandari, W. (2024). Forecasting the Export Unit Value Index in Indonesia Using the Single Input Transfer Function. KnE Life Sciences, 2024, 218-228.
Miroudot, S., R. Lanz and A. Ragoussis (2009). Trade in Intermediate Goods and Service. OECD Trade Policy Papers, No. 93, OECD Publishing, Paris. http://dx.doi.org/10.1787/5kmlcxtdlk8r-en
Mutreja, P., Ravikumar, B., & Sposi, M. (2018). Capital goods trade, relative prices, and economic development. Review of Economic Dynamics, 27, 101-122.
Nooraeni, R., Nickelson, J., Rahmadian, E., & Yudho, N. P. (2022). New recommendation to predict export value using big data and machine learning technique. Statistical Journal of the IAOS, 38(1), 277-290.
Özden, E. (2022). The Dynamics Affecting the Export-Import Ratio in Turkey: A Hybrid Model Proposal with Econometrics and Machine Learning Approach. Journal of Economic Policy Researches, 9(2), 265-291.
Pushpalatha, K. R., & Karegowda, A. G. (2017, December). CFS based feature subset selection for enhancing classification of similar looking food grains-a filter approach. In 2017 2nd international conference on emerging computation and information technologies (ICECIT) (pp. 1-6). IEEE.
Quinlan, J. R. (1992, November). Learning with continuous classes. In 5th Australian joint conference on artificial intelligence (pp. 343-348).
Rouzegari, N., Hassanzadeh, Y., & Sattari, M. T. (2019). Using the hybrid simulated annealing-M5 tree algorithms to extract the if-then operation rules in a single reservoir. Water Resources Management, 33(10), 3655-3672.
Sattari, M. T., Mirabbasi, R., Sushab, R. S., & Abraham, J. (2018). Prediction of groundwater level in Ardebil plain using support vector regression and M5 tree model. Groundwater, 56(4), 636-646.
Shahzad, U., & Miao, C. (2025). Analysis of Chinese economic growth under technology and consumer components of terms of trade: a time series study (1980–2021). Discover Sustainability, 6(1), 1294.
Sharma, M. (2022). Improved autistic spectrum disorder estimation using Cfs subset with greedy stepwise feature selection technique. International Journal of Information Technology, 14(3), 1251-1261.
Silver, M. (2009). Do unit value export, import, and terms-of-trade indices misrepresent price indices?. IMF Staff Papers, 56(2), 297-322.
Suler, P., Rowland, Z., & Krulicky, T. (2021). Evaluation of the accuracy of machine learning predictions of the Czech Republic’s exports to the China. Journal of Risk and Financial Management, 14(2), 76.
Sultanova, G. (2024). Trends in Development and Diversification of Exports of the Republic of Uzbekistan. Economic Development and Analysis, 2(10), 232-249.
Sulthana, R., & Ramesh, P. (2022). Predicting The Import and Export of Commodities Using Support Vector Regression and Long Short-Term Prediction. Int. J. Com. Dig. Sys, 11(1).
Szczygielski, K., & Grabowski, W. (2012). Are unit export values correct measures of the exports’ quality?. Economic Modelling, 29(4), 1189-1196.
Wang, Y. & Witten, I. H. (1996). Induction of model trees for predicting continuous classes. (Working paper 96/23). Hamilton, New Zealand: University of Waikato, Department of Computer Science.
Wilkinson, J. (2012). The food processing industry, globalization and developing countries. In The transformation of agri-food systems (pp. 87-108). Routledge.
Yuksel, O., Bayraktar, M., & Sokukcu, M. (2023). Comparative study of machine learning techniques to predict fuel consumption of a marine diesel engine. Ocean Engineering, 286, 115505.
Zhu, Q. (2025). Predicting the Total Export-import Volume of China's Economic Trade through Machine Learning. International Journal of Mathematical, Engineering & Management Sciences, 10(1), 63-75.

Ayrıntılar

Birincil Dil

İngilizce

Konular

Ekonometrik ve İstatistiksel Yöntemler

Bölüm

Araştırma Makalesi

Yazarlar

Enes Filiz ^*
0000-0002-8006-9467
Türkiye

Yayımlanma Tarihi

15 Ekim 2026

Gönderilme Tarihi

2 Ocak 2026

Kabul Tarihi

23 Nisan 2026

Yayımlandığı Sayı

Yıl 2026 Cilt: 11 Sayı: 2

IZ

https://izlik.org/JA68LW56HN

APA

Filiz, E. (2026). DETERMINING THE PREDICTION OF THE EXPORT UNIT VALUE INDEX USING THE M5 RULES MACHINE LEARNING ALGORITHM. Akademik İzdüşüm Dergisi, 11(2), 108-121. https://izlik.org/JA68LW56HN

AMA

1.Filiz E. DETERMINING THE PREDICTION OF THE EXPORT UNIT VALUE INDEX USING THE M5 RULES MACHINE LEARNING ALGORITHM. AİD. 2026;11(2):108-121. https://izlik.org/JA68LW56HN

Chicago

Filiz, Enes. 2026. “DETERMINING THE PREDICTION OF THE EXPORT UNIT VALUE INDEX USING THE M5 RULES MACHINE LEARNING ALGORITHM”. Akademik İzdüşüm Dergisi 11 (2): 108-21. https://izlik.org/JA68LW56HN.

EndNote

Filiz E (01 Ekim 2026) DETERMINING THE PREDICTION OF THE EXPORT UNIT VALUE INDEX USING THE M5 RULES MACHINE LEARNING ALGORITHM. Akademik İzdüşüm Dergisi 11 2 108–121.

IEEE

[1]E. Filiz, “DETERMINING THE PREDICTION OF THE EXPORT UNIT VALUE INDEX USING THE M5 RULES MACHINE LEARNING ALGORITHM”, AİD, c. 11, sy 2, ss. 108–121, Eki. 2026, [çevrimiçi]. Erişim adresi: https://izlik.org/JA68LW56HN

ISNAD

Filiz, Enes. “DETERMINING THE PREDICTION OF THE EXPORT UNIT VALUE INDEX USING THE M5 RULES MACHINE LEARNING ALGORITHM”. Akademik İzdüşüm Dergisi 11/2 (01 Ekim 2026): 108-121. https://izlik.org/JA68LW56HN.

JAMA

1.Filiz E. DETERMINING THE PREDICTION OF THE EXPORT UNIT VALUE INDEX USING THE M5 RULES MACHINE LEARNING ALGORITHM. AİD. 2026;11:108–121.

MLA

Filiz, Enes. “DETERMINING THE PREDICTION OF THE EXPORT UNIT VALUE INDEX USING THE M5 RULES MACHINE LEARNING ALGORITHM”. Akademik İzdüşüm Dergisi, c. 11, sy 2, Ekim 2026, ss. 108-21, https://izlik.org/JA68LW56HN.

Vancouver

1.Enes Filiz. DETERMINING THE PREDICTION OF THE EXPORT UNIT VALUE INDEX USING THE M5 RULES MACHINE LEARNING ALGORITHM. AİD [Internet]. 01 Ekim 2026;11(2):108-21. Erişim adresi: https://izlik.org/JA68LW56HN

2016-2026 Akademik İzdüşüm Dergisi

e-ISSN: 2547-9725

Dergimizde yayımlanan tüm makaleler Creative Commons Atıf-GayriTicari 4.0 Uluslararası (CC BY-NC 4.0) Lisansı ile korunmaktadır. Bu kapsamda eserler; ticari amaç gütmemek ve orijinal kaynağa eksiksiz atıf yapmak koşuluyla kopyalanabilir, dağıtılabilir ve üzerinde düzenleme yapılabilir.

İhracat Birim Değer Endeksinin M5 Kural Tabanlı Makine Öğrenmesi Algoritması Ile Tahmininin Belirlenmesi

Öz

Anahtar Kelimeler

Destekleyen Kurum

Etik Beyan

Teşekkür

DETERMINING THE PREDICTION OF THE EXPORT UNIT VALUE INDEX USING THE M5 RULES MACHINE LEARNING ALGORITHM

Öz

Anahtar Kelimeler

Destekleyen Kurum

Etik Beyan

Teşekkür

Kaynakça

Ayrıntılar

Birincil Dil

Konular

Bölüm

Yazarlar

Yayımlanma Tarihi

Gönderilme Tarihi

Kabul Tarihi

Yayımlandığı Sayı

IZ

Kaynak Göster