Yapay Sinir Ağları ile Türkiye Kâğıt ve Kâğıt Ürünleri Sektörü İthalat Tahmini

Öz

Kâğıt ve kâğıt ürünleri sektörü, Türkiye ekonomisinde önemli bir yere sahip olup, diğer sektörlerle etkileşim içerisindedir. Türkiye, büyük miktarlarda kâğıt ithal etmekte ve bu ithalat, sektörün büyümesi ve sürdürülebilirliği açısından hayati öneme sahiptir. Doğru ithalat tahmini, stratejik planlama ve kaynak yönetimi için gereklidir. Bu çalışma, Türkiye kâğıt sektörünün 2023 Nisan - 2024 Mart dönemi ithalatını öngörmeyi amaçlamaktadır. Bu amaçla Multilayer Perceptron (MLP) ve Radial Basis Function (RBF) olmak üzere iki farklı yapay sinir ağı modeli kullanılmıştır. Türkiye İstatistik Kurumu'ndan (TÜİK) elde edilen veri seti, 2005 ile 2023 yılları arasındaki 219 aylık veriyi kapsamaktadır. Modelin bağımlı değişkeni, Türkiye'nin aylık kâğıt ve kâğıt ürünleri ithalat değeri olup, bağımsız değişkenler ise aylık ortalama Amerikan Doları kuru, Türkiye aylık ithalatı, İmalat Sanayi Üretim Endeksi, Kâğıt Üretim Endeksi ve Türkiye aylık kâğıt ve kâğıt ürünleri ihracatıdır. MLP modeli, aylık kâğıt ve kâğıt ürünleri ithalatının 270 ile 300 milyon USD arasında olacağını tahmin ederken, RBF modeli tahmin değerlerini 268 ile 321 milyon USD arasında öngörmektedir. Bu bulgular, yapay sinir ağlarının doğru ve güvenilir tahminler yapma konusunda önemli başarılar sağladığını göstermektedir. Bu çalışma, kâğıt ve kâğıt ürünleri sektöründe ithalatı öngörmek için yapay sinir ağı yöntemlerinin uygulanmasıyla literatürdeki bir boşluğu doldurmakta ve şirketlerin envanter yönetimi, üretim planlaması ve pazarlama stratejileri konusunda daha bilinçli kararlar almasına yardımcı olabilecek yenilikçi bir yaklaşım sunmaktadır. Yapay sinir ağlarının gelişmiş hesaplama gücü ve desen tanıma yeteneklerinden yararlanarak, çalışma, kâğıt ve kâğıt ürünleri endüstrisinde stratejik planlama süreçlerini geliştirmeyi amaçlamaktadır. Geleneksel yöntemler genellikle ticaret verilerinin analizinde ve tahmininde kullanılırken, ekonomik verilerdeki karmaşık ve doğrusal olmayan ilişkileri yakalamakta sınırlı kalmaktadır. Bu çalışmanın yapay sinir ağı uygulamaları, bu tür karmaşıklıkları daha iyi yönetebilen modeller kullanarak önemli bir ilerleme sunmaktadır. MLP ve RBF modellerinin doğruluğu, bunların ekonomik tahminlerde değerli araçlar olma potansiyelini vurgulamaktadır ve tedarik zinciri operasyonlarını optimize etmek ve pazar yanıt verebilirliğini artırmak için kritik bilgiler sağlamaktadır. Sonuçlar, gelecekteki ithalat gereksinimlerini etkili bir şekilde tahmin ederek, şirketlerin operasyonel performanslarını iyileştirebileceğini ve müşteri memnuniyetini artırabileceğini göstermektedir. Bu çalışmanın özgünlüğü, geleneksel yöntemlerin hakim olduğu bir sektörde ithalat değerlerini tahmin etmek için yapay sinir ağı modellerini kullanmasında yatmaktadır. Bu yenilikçi yaklaşım, mevcut bilgi birikimine katkıda bulunmakla kalmayıp, aynı zamanda sektördeki işletmeler için pratik uygulamalar sunmaktadır. Verilerin detaylı analizi ve kullanılan güçlü modelleme teknikleri, kâğıt ithalatının dinamiklerini anlamak ve doğru tahminler yaparak stratejik kararlar almak için kapsamlı bir çerçeve sağlamaktadır. Sonuç olarak, bu çalışma, Türkiye kâğıt ve kâğıt ürünleri sektöründe ithalat değerlerini tahmin etmede yapay sinir ağlarının önemli başarılarını göstermektedir. Bulgular, şirketlerin stratejik planlama yaparken envanter yönetimi, üretim planlaması ve pazarlama stratejileri geliştirme yeteneklerini artırabilecek değerli bilgiler sağlamaktadır. Araştırma, yenilikçi yaklaşımıyla literatürdeki bir boşluğu doldurarak, sektörün karar verme süreçlerini iyileştirmek için yeni perspektifler ve pratik uygulamalar sunmaktadır.

Anahtar Kelimeler

• Yapay Sinir Ağları Modelleri
• Çok Katmanlı Algılayıcılar
• Radyal Tabanlı Fonksiyon
• Kâğıt ve Kâğıt Ürünleri
• Zaman Serileri

Forecasting Türkiye's Paper and Paper Products Sector Import Using Artificial Neural Networks

Öz

The paper and paper products sector is a crucial component of the Turkish economy, characterized by significant interactions with various other sectors. Türkiye imports substantial amounts of paper, playing a vital role in the growth and sustainability of this sector. Accurate import forecasting is essential for strategic planning and resource management. This study aims to forecast the imports of the Turkish paper sector for the period from April 2023 to March 2024 using two artificial neural network (ANN) models: Multilayer Perceptron (MLP) and Radial Basis Function (RBF). The dataset, obtained from the Turkish Statistical Institute (TurkStat), covers 219 months of data from 2005 to 2023. The dependent variable is Türkiye’s monthly import value of paper and paper products, while the independent variables include the monthly average US Dollar exchange rate, monthly imports of Türkiye, the Manufacturing Industry Production Index, the Paper Production Index, and the monthly exports of paper and paper products from Türkiye. The MLP model forecasts that the monthly imports of paper and paper products will range between 270 to 300 million USD, while the RBF model predicts values between 268 and 321 million USD. These findings underscore the efficacy of ANNs in providing accurate and reliable forecasts. This study addresses a gap in the literature by applying ANN methods to forecast imports in the paper and paper products sector, presenting a novel approach that can assist companies in making better-informed decisions regarding inventory management, production planning, and marketing strategies. By leveraging the advanced computational power and pattern recognition capabilities of ANNs, the study aims to enhance the strategic planning processes in the paper and paper products industry. The traditional methods often used in trade data analysis and forecasting are limited in capturing the complex and non-linear relationships present in economic data. This study's application of ANNs offers a significant advancement by utilizing models that can better handle such complexities. The accuracy of the MLP and RBF models highlights their potential as valuable tools for economic forecasting, providing insights that are crucial for optimizing supply chain operations and improving market responsiveness. The results indicate that companies can achieve better operational performance and increased customer satisfaction by effectively forecasting future import requirements. The originality of this study lies in its methodological approach, utilizing ANN models to forecast import values in a sector where traditional methods have been predominant. This innovative approach not only contributes to the existing body of knowledge but also offers practical applications for businesses within the sector. The detailed analysis of the data, combined with the robust modeling techniques employed, provides a comprehensive framework for understanding the dynamics of paper imports and making strategic decisions based on accurate predictions. In conclusion, the study demonstrates the significant success of artificial neural networks in predicting import values for the Turkish paper and paper products sector. The findings provide valuable information that can aid companies in strategic planning, enhancing their ability to manage inventory, plan production, and develop effective market strategies. The research contributes to the literature by filling a gap with its innovative approach, offering new perspectives and practical applications for improving decision-making processes in the industry.

Anahtar Kelimeler

• Artificial Neural Networks Models
• Multi-Layer Perceptron (MLP)
• Radial Basis Function (RBF)
• Paper and Paper Products
• Time Series

Kaynakça

1. Akyüz, K. C., Yildirim, İ., Akyüz, İ., & Tugay, T. (2017). Investigation of Financial Performance of Companies in the Sector of Paper and Paper Products Operating in Borsa İstanbul, 4. Uluslarrası Mobilya ve Dekorasyon Kongresi, 2017. Retrieved from: https://avesis.ktu.edu.tr/yayin/0c6abce5-71ac-4340-aee6-97b57f8a3299/investigation-of-financial-performance-of-companies-in-the-sector-of-paper-and-paper-products-operating-in-borsa-istanbul
2. Anderton, B. (1999). Innovation, product quality, variety, and trade performance: an empirical analysis of Germany and the UK. Oxford Economic Papers, 51(1), 152-167. https://doi.org/10.1093/oep/51.1.152
3. Barrow, D. K. & Kourentzes, N. (2016). Distributions of forecasting errors of forecast combinations: implications for inventory management. International Journal of Production Economics, 177, 24-33. https://doi.org/10.1016/j.ijpe.2016.03.017
4. Buhmann, M. D. (2000). Radial basis functions. Acta numerica, 9, 1-38. https://doi.org/10.1017/S0962492900000015
5. Central Bank of the Republic of Türkiye Electronic Data Distribution System (CBRT-EVDS), https://evds2.tcmb.gov.tr/index.php?/evds/serieMarket Access Date: 27.06.2023
6. Crespo, N., & Fontoura, M. P. (2007). Determinant factors of FDI spillovers–what do we really know?. World development, 35(3), 410-425. https://doi.org/10.1016/j.worlddev.2006.04.001
7. Dumor, K., & Yao, L. (2019). Estimating china’s trade with its partner countries within the belt and road initiative using neural network analysis. Sustainability, 11(5), 1449. https://doi.org/10.3390/su11051449
8. Egrioğlu, E., & Bas, E. (2023). A new deep neural network for forecasting: deep dendritic artificial neural network.. https://doi.org/10.21203/rs.3.rs-2913556/v1

9. Eşidir, K. A. , Gür, Y. E. , Yoğunlu, V. & Çubuk, M. (2022). Forecasting of Monthly Zero km Car Sales in Turkey with Artificial Neural Networks (ANN) and ARIMA Models. Pamukkale University Journal of Business Research, 9(2) , 260-277. https://doi.org/10.47097/piar.1132101
10. Faraji, J., Ketabi, A., Hashemi‐Dezaki, H., Shafie‐khah, M., & Catalão, J. P. (2020). Optimal day-ahead scheduling and operation of the prosumer by considering corrective actions based on very short-term load forecasting. IEEE Access, 8, 83561-83582. https://doi.org/10.1109/access.2020.2991482
11. General Directorate of Industry, (2022). Paper Sector Report 2021, T.C. Ministry of Industry and Technology, pp. 7-23.
12. Goldberg, P. K., & Knetter, M. M. (1996). Goods prices and exchange rates: What have we learned?, Journal of Economic literature, 35(3),1-42. https://doi.org/10.3386/w5862
13. Grossman, G. M., & Helpman, E. (1995). Trade wars and trade talks. Journal of political Economy, 103(4), 675-708. https://doi.org/10.1086/261999
14. Gujarati, D. N. (2003). Basic Econometrics, McGraw Hill, Newyork
15. Hagan, M. T., Demuth, H. B., & Beale, M. (1997). Neural network design. PWS Publishing Co.
16. Hyndman, R. J., & Koehler, A. B. (2006). Another look at measures of forecast accuracy. International journal of forecasting, 22(4), 679-688. https://doi.org/10.1016/j.ijforecast.2006.03.001
17. Karadeniz, E., Iskenderoglu, Ö., & Cemile, Ö. (2021). Scale-Based Analysis of the Financial Performance of the Paper and Paper Products Manufacturing Sector: A Study on the Sector Balance Sheets of the Central Bank of the Republic of Turkey. Journal of Bartın Faculty of Forestry, 23(1), 160-171. https://doi.org/10.24011/barofd.891992
18. Khashei, M., & Bijari, M. (2010). An artificial neural network (p, d, q) model for timeseries forecasting. Expert Systems with Applications, 37(1), 479-489. https://doi.org/10.1016/j.eswa.2009.05.044
19. Kilimci, Z. H., Akyuz, A. O., Akyokuş, S., Uysal, M., Bülbül, B. A., & Ekmis, M. A. (2019). An improved demand forecasting model using deep learning approach and proposed decision integration strategy for supply chain. Complexity, 1-15. https://doi.org/10.1155/2019/9067367
20. Kmiecik, M. (2023). Supporting of manufacturer’s demand plans as an element of logistics coordination in the distribution network. Production Engineering Archives, 29(1), 69-82. https://doi.org/10.30657/pea.2023.29.9
21. Kuan, C. M., & Liu, T. (1995). Forecasting exchange rates using feedforward and recurrent neural networks. Journal of Applied Econometrics, 10(4), 347-364. https://doi.org/10.1002/jae.3950100403
22. Kumar, R.R., Thenmozhi, M. (2006). Forecasting Stock Index Movement: A Comparison of Support Vector Machines and Random Forest. 9th Capital Markets Conference, Indian Institute of Capital Markets Paper. http://dx.doi.org/10.2139/ssrn.876544
23. Kurniawan, I., Silaban, L. S., & Munandar, D. (2020). Implementation of convolutional neural network and multilayer perceptron in predicting air temperature in padang. Jurnal RESTI (Rekayasa Sistem Dan Teknologi Informasi), 4(6). https://doi.org/10.29207/resti.v4i6.2456
24. Lancaster, K. J. (1966). A new approach to consumer theory. Journal of Political Economy, 74(2), 132-157. https://doi.org/10.1086/259131
25. Looney, C. G. (1996). Advances in feedforward neural networks: demystifying knowledge acquiring black boxes. IEEE Transactions on Knowledge and Data Engineering, 8(2), 211-226. https://doi.org/10.1109/69.494162
26. Mai, W., Chung, C. Y., Wu, T., & Wong, W. C. (2014, July). Electric load forecasting for large office building based on radial basis function neural network. In 2014 IEEE PES General Meeting| Conference & Exposition (pp. 1-5). IEEE. 1 https://doi.org/0.1109/PESGM.2014.6939378
27. Momeneh, S. & Nourani, V. (2022). Forecasting of groundwater level fluctuations using a hybrid of multi-discrete wavelet transforms with artificial intelligence models. Hydrology Research, 53(6), 914-944. https://doi.org/10.2166/nh.2022.035
28. Muhamad, S., Sofean, S. H., Moktar, B., & Shahidan, W. N. W. (2021). Fuzzy time series and artificial neural network: forecasting exportation of natural rubber in malaysia. Journal of Computing Research and Innovation, 6(1), 22-30. https://doi.org/10.24191/jcrinn.v6i1.170
29. Pala, T. & Camurcu, A. Y. (2016). Design of decision support system in the metastatic colorectal cancer data set and its application. Balkan Journal of Electrical and Computer Engineering, 4(1). https://doi.org/10.17694/bajece.23930
30. Prechelt, L. (1998). Early Stopping - But When? In G. Orr and K.-R. Müller (Eds.), Neural Networks: Tricks of the Trade. Springer. https://doi.org/10.1007/978-3-642-35289-8
31. Refenes, A. P., Zapranis, A., & Francis, G. (1994). Stock performance modeling using neural networks: a comparative study with regression models. Neural Networks, 7(2), 375-388. https://doi.org/10.1016/0893-6080(94)90030-2
32. Riedmiller, M., & Braun, H. (1993). A direct adaptive method for faster backpropagation learning: the RPROP algorithm. In IEEE International Conference on Neural Networks (pp. 586-591). IEEE. https://doi.org/10.1109/ICNN.1993.298623
33. Safa, B., Arkebauer, T. J., Zhu, Q., Suyker, A., & Irmak, S. (2021). Gap filling of net ecosystem co<sub>2</sub> exchange (nee) above rain-fed maize using artificial neural networks (anns). Journal of Software Engineering and Applications, 14(05), 150-171. https://doi.org/10.4236/jsea.2021.145010
34. Sanders, N. R. & Ritzman, L. P. (2004). Using warehouse workforce flexibility to offset forecast errors. Journal of Business Logistics, 25(2), 251-269. https://doi.org/10.1002/j.2158-1592.2004.tb00189.x
35. Sekeroglu, B. and Tuncal, K. (2021). Prediction of cancer incidence rates for the european continent using machine learning models. Health Informatics Journal, 27(1), 146045822098387. https://doi.org/10.1177/1460458220983878
36. Shin, Y. C. (1994). Radial basis function neural network for approximation and estimation of nonlinear stochastic dynamic systems. IEEE Transactions on Neural Networks, 5(4), 594-603. https://doi.org/10.1109/72.298229
37. Siami-Irdemoosa, E., & Dindarloo, S. R. (2015). Prediction of fuel consumption of mining dump trucks: A neural networks approach. Applied Energy, 151, 77-84. https://doi.org/10.1016/j.apenergy.2015.04.064.
38. Towfiqul, A. R. M., Pal, S. C., Chakrabortty, R., Mallick, J., Sarkar, S. K., Fattah, M. A., … & Rahman, M. S. (2022). Multilayer perception and radial basis function models for predicting trends of rainfall in asian megacity Dhaka,Bangladesh.. https://doi.org/10.21203/rs.3.rs-1720286/v1
39. Turkish Statistical Institute (TurkStat), (2023). Retrieved from: www.tuik.gov.tr. Access Date: 05.06.2023
40. Wang, Y., Ni, X. S., & Stone, B. (2018). A two-stage hybrid model by using artificial neural networks as feature construction algorithms. https://doi.org/10.48550/arXiv.1812.02546
41. Zhang, G. P. (2003). Time series forecasting using a hybrid ARIMA and neural network model. Neurocomputing, 50, 159-175. https://doi.org/10.1016/S0925-2312(01)00702-0
42. Zhang, G., Patuwo, B. E., & Hu, M. Y. (1998). Forecasting with artificial neural networks:: The state of the art. International Journal of Forecasting, 14(1), 35-62. https://doi.org/10.1016/S0169-2070(97)00044-7