YAPAY SİNİR AĞLARI İLE TÜRKİYE PLASTİK SEKTÖRÜ İTHALAT TAHMİNİ: 2023 YILI NİSAN-ARALIK AYLARI

Yıl 2023, Cilt: 10 Sayı: 23, 91 - 114, 31.12.2023

Kamil Abdullah Eşidir , Yunus Emre Gür

https://doi.org/10.58884/akademik-hassasiyetler.1307536

Cited By: 1

Öz

Plastik malzemeler, günümüzde birçok endüstriyel ve tüketici ürününün üretiminde önemli bir rol oynamaktadır. Türkiye gibi gelişmekte olan ülkelerde, endüstriyel büyüme ve nüfus artışı gibi faktörler plastik talebini artırmaktadır. Bu talebin karşılanması için de Türkiye gibi ülkeler, çoğunlukla ithalat yoluyla plastik malzemeleri temin etmektedirler. Dolayısıyla, Türkiye adına ekonomik açıdan oldukça önemli bir potansiyele sahip olan plastik sektörünün ithalat değerinin tahmin edilmesi önem arz etmektedir.
Bu çalışma, yapay sinir ağları (YSA) kullanarak, Türkiye’nin plastik sektöründeki gelecek ithalat değerini tahmin etmeyi amaçlamaktadır. Çalışmada kullanılan veriler, Türkiye İstatistik Kurumundan (TÜİK) ve Türkiye Cumhuriyet Merkez Bankasından (TCMB) edinilmiştir. Veri seti 2000 ile 2023 yılları arasındaki aylık verileri (267 ay) kapsamaktadır. Modelin bağımlı değişkeni, Türkiye aylık plastik ithalat değeridir. Bununla birlikte, modelin 6 adet bağımsız değişkeni vardır. Bunlar; aylık ortalama Amerikan Doları Kuru, aylık Türkiye ihracatı, aylık Türkiye ithalatı, plastik üretici fiyat endeksi (ÜFE), aylık Avrupa petrol varil fiyatı ve aylık plastik ihracat değeridir. Çalışmanın sonuçları, 2023 yılı Nisan-Aralık ayları arasında, Türkiye’nin aylık plastik ithalatının 1,25 ile 1,45 milyar USD arasında gerçekleşeceğini göstermektedir. Ayrıca bu çalışma, Türkiye plastik ithalatının tahmin edilmesinde YSA modellerinin potansiyelini vurgulamaktadır. Gelecekteki çalışmalar, daha kapsamlı veri setleri, daha karmaşık sinir ağı mimarileri ve farklı ekonomik değişkenlerin etkilerini dahil ederek tahmin performansını daha da iyileştirmeyi hedefleyebilir.

Anahtar Kelimeler

Yapay Sinir Ağları, MultiLayer Perceptron, Arima, İthalat, Plastik Sektörü

TURKISH PLASTICS INDUSTRY IMPORT FORECAST WITH ARTIFICIAL NEURAL NETWORKS: APRIL-DECEMBER 2023

Öz

Plastic materials play an important role in the production of many industrial and consumer products today. In developing countries such as Turkey, factors such as industrial growth and population growth increase the demand for plastics. In order to meet this demand, countries such as Turkey mostly supply plastic materials through imports. Therefore, it is important to estimate the import value of the plastics industry, which has a very important economic potential for Turkey.
This study aims to predict the future import value of Turkey's plastics industry by using artificial neural networks (ANN). The data used in the study were obtained from the Turkish Statistical Institute (TURKSTAT) and the Central Bank of the Republic of Turkey (CBRT). The data set includes monthly data (267 months) between 2000 and 2023. The dependent variable of the model is Turkey's monthly plastic import value. The model has 6 independent variables. These; monthly average US Dollar Rate, monthly Turkey export, monthly Turkey import, plastic producer price index (PPI), monthly European oil barrel price and monthly plastic export value. The results of the study show that Turkey's monthly plastic import will be between 1.25 and 1.45 billion USD between April and December 2023. In addition, this study highlights the potential of ANN models in estimating plastic imports in Turkey. Future work may aim to further improve forecasting performance by incorporating more comprehensive datasets, more complex neural network architectures, and the effects of different economic variables.

Anahtar Kelimeler

Artificial Neural Networks, MultiLayer Perceptron, Arima, Import, Plastic Sector

Kaynakça

• Alam, T. (2019). Forecasting exports and imports through artificial neural network and autoregressive integrated moving average. Decision Science Letters, 8, 249–260.
• Arminarahmah, N., Rizki, S. D., Putra, O. A., & Wanto, A. (2022). Performance analysis and model determination for forecasting aluminum imports using the Powell-Beale algorithm. International Journal of Information System and Technology, 5(5), 624-632.
• Barrowclough, D., & Birkbeck, C. D. (2022). Transforming the global plastics economy: the role of economic policies in the global governance of plastic pollution. Social Sciences, 11(1), 26.
• Batarseh, F., Gopinath, M., Nalluru, G., & Beckman, J. (2019). Application of machine learning in forecasting international trade trends. ArXiv:1910.03112.
• d’Ambrières, W. (2019). Plastics recycling worldwide: current overview and desirable changes.  The Journal of Field Actions, (Special Issue 19), 12-21.
• Eris, E. D., Ozer, P. S., & Ozmen, O. N. T. (2012). Strategic and market oriented behaviors in Turkish plastics industry. International Journal of Business And Management Studies, 4(1), 87-99.
• Eşidir, K. A. , Gür, Y. E. , Yoğunlu, V. & Çubuk, M. (2022). Yapay Sinir Ağları (YSA) ve ARIMA Modelleri ile Türkiye’de aylık sıfır km otomobil satış adetlerinin tahmin edilmesi. Pamukkale Üniversitesi İşletme Araştırmaları Dergisi, 9(2), 260-277.
• Geyer, R., Jambeck, J. R., & Law, K. L. (2017). Production, use, and fate of all plastics ever made. Science Advances, 3(7), 1-5.
• Gourmelon, G. (2015). Global plastic production rises, recycling lags. Vital Signs, 22, 91-95.
• Gujarati, D. N. (2003). Basic econometrics. McGraw Hill: Newyork.
• Halde, R. U. (2010). Plastics and health Risks. T. B. Center for environmental biotechnology içinde, The Annual Review of Public Health, 179–194. Baltimore, Maryland: Center for Water and Health, Bloomberg School of Public Health, Johns Hopkins University.
• Kavaklıoğlu, K., Ceylan, H., Öztürk, H. K., & Canyurt, O. E. (2009). Modeling and prediction of Turkey’s electricity consumption using artificial neural networks. Energy Conversion and Management, 50(11), 2719-2727.
• Kukreja, H., Bharath, N., Siddesh, C.S., Kuldeep, S. (2016), An introduction to artificial neural network. International Journal of Advance Research and Innovative Ideas in Education, 1, 27-30.
• Kuo, R. J., & Li, P. S. (2016). Taiwanese export trade forecasting using firefly algorithm based k-means algorithm and svr with wavelet transform. Computers & Industrial Engineering, 99, 153–161. https://doi.org/10.1016/j.cie.2016.07.012.
• Park, Y. S., & Lek, S. (2016). Artificial neural networks: Multilayer perceptron for ecological modeling. In Developments in environmental modelling, 28, 123-140.
• Shen, M.-L., Lee, C.-F., Liu, H.-H., Chang, P.-Y., & Yang, C.-H. (2021). Effective multinational trade forecasting using lstm recurrent neural network. Expert Systems with Applications, 182, Article 115199. https://doi.org/10.1016/j.eswa.2021.115199.
• 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.
• Sun, Y., Zhang, X., & Wang, S. (2020). A hierarchical forecasting model for china’s foreign trade. Journal of Systems Science and Complexity, 33, 743–759. https://doi. org/10.1007/s11424-020-8070-y.
• Temurçin, K. (2015). Large scale industrial enterprises in Turkish industry: Their structures, characteristics and spatial distribution. Prace Komisji Geografii Przemysłu Polskiego Towarzystwa Geograficznego, 29(1), 89-112.
• Türkiye Cumhuriyet Merkez Bankası Elektronik Veri Dağıtım Sistemi (2023, 5 Mayıs). 20 Mayıs 2023 tarihinde https://evds2.tcmb.gov.tr/index.php?/evds/serieMarket adresinden erişilmiştir.
• Türkiye İstatistik Kurumu (2023, 18 Mayıs), www.tuik.gov.tr
• Veenstra, A. W., & Haralambides, H. E. (2001). Multivariate autoregressive models for forecasting seaborne trade flows. Transportation Research Part E: Logistics and Transportation Review, 37, 311–319. https://doi.org/10.1016/S1366-5545(00) 00020-X.
• Wang, Y., Wei, W., Bi, Z., Cao, R., Li, J., Shu, D., & Lou, Z. (2021). Decomposing the decoupling of plastics consumption and economic growth in G7 and China: Evidence from 2001 to 2020 based on China's import ban. Journal of Environmental Management, 296, 113225.
• Wang, Y.-H., & Lee, J.-D. (2012). Estimating the import demand function for china. Economic Modelling, 29, 2591–2596. https://doi.org/10.1016/j.econmod.2012.08.
• Wanto, A., Hayadi, B. H., Subekti, P., Sudrajat, D., Wikansari, R., Bhawika, G. W., ... & Surya, S. (2019). Forecasting the export and import volume of crude oil, oil products and gas using ANN. In Journal of Physics: Conference Series, 1255, No. 1, p. 012016.
• Wen, Z., Xie, Y., Chen, M., & Dinga, C. D. (2021). China’s plastic import ban increases prospects of environmental impact mitigation of plastic waste trade flow worldwide. Nature communications, 12(1), 425.
• Wibowo, S. M., Hakim, D. B., Barus, B., & Fauzi, A. (2022). Estimation of Energy Demand in Indonesia using Artificial Neural Network. International Journal of Energy Economics and Policy, 12(6), 261.
• Yildizhan, F. S. (2021). A Technical and Industrial Analysis of Global Plastics Market, Trade, Financing, and Operations. ScienceOpen Preprints.
• Yu, L., Wang, S., & Lai, K. K. (2008). Forecasting China’s foreign trade volume with a kernel-based hybrid econometric-ai ensemble learning approach. Journal of Systems Science and Complexity, 21, 1–19. https://doi.org/10.1007/s11424-008-9062-5.
• Zhu, S., & Gong, S. (2023). Research on weighted directed dynamic multiplexing network of world grain trade based on improved mlp framework. Journal of Computer and Communications, 11(7), 191-207.