Prediction of Turkey's cotton sock exports to Germany using deep learning approach

Öz

Cotton socks are a strategic export product for Turkey. Therefore, the aim of this study is to forecast Turkey's exports to Germany, the world's largest cotton socks market. In order to achieve this objective, the determinants of exports were identified by analysing the literature. Then, expert opinion was sought to determine the importance of these factors for Turkey's cotton socks exports to Germany. Using the deep learning model created from the factors determined as a result of the expert opinion, the prediction of the export of Turkish socks to Germany was realised. A success rate of 96% was achieved with the prediction.

Anahtar Kelimeler

• Deep learning
• MLP neural network
• cotton sock
• export prediction

TÜRKİYE'NİN ALMANYA'YA PAMUKLU ÇORAP İHRACATININ DERİN ÖĞRENME YAKLAŞIMI İLE TAHMİNİ

Öz

Pamuklu çoraplar Türkiye için stratejik bir ihraç ürünüdür. Bu nedenle, bu çalışmanın amacı Türkiye'nin dünyanın en büyük pamuklu çorap pazarı olan Almanya'ya ihracatını tahmin etmektir. Bu amaca ulaşmak için, literatür analiz edilerek ihracatın belirleyicileri tespit edilmiştir. Daha sonra, bu faktörlerin Türkiye'nin Almanya'ya pamuklu çorap ihracatı açısından önemini belirlemek için uzman görüşüne başvurulmuştur. Uzman görüşü sonucunda belirlenen faktörlerden oluşturulan derin öğrenme modeli kullanılarak Türkiye'nin Almanya'ya çorap ihracatının tahmini gerçekleştirilmiştir. Tahmin ile %96' lık bir başarı oranı elde edildi.

Anahtar Kelimeler

• Derin Öğrenme
• MLP yapay sinir ağı
• pamuklu çorap
• ihracat tahmini

Kaynakça

1. Yildiz, A. & Özbek, A., (2020). Selection of socks export markets for Turkey using multi-criteria decision making methods. Sigma Journal of Engineering and Natural Sciences, 38(2), 795-815.
2. Avşar, İ. İ., & Ecemı̇ş, O., (2023). Forecast of turkey’s import and export by data mining methods. Osmaniye Korkut Ata University Journal of The Institute of Science and Technology, 6(3), 1890–1907. https://doi.org/10.47495/okufbed.1220874
3. Awasthi, S., SenGupta, I., Wilson, W., & Lakkakula, P., (2022). Machine learning and neural network based model predictions of soybean export shares from US Gulf to China. Statistical Analysis and Data Mining, 15(6), 707–721. https://doi.org/10.1002/ sam.11595
4. Bin, J., & Tianli, X., (2020). Forecast of export demand based on artificial neural network and fuzzy system theory. Journal of Intelligent & Fuzzy Systems, 39(2), 1701–1709. https://doi.org/ 10.3233/ jifs-179944
5. Çakan, V. A., (2020). Forecasts for Turkey Fresh Fig Production and Dried Fig Export: ARIMA Model Approach. Journal of Tekirdag Agricultural Faculty, 17(3), 357–368. https://doi.org/ 10.33462/jotaf.684893
6. Han, Z., Zhu, Z., Zhao, S., & Dai, W., (2022). Research on nonlinear forecast and influencing factors of foreign trade export based on support vector neural network. Neural Computing & Applications, 34(4), 2611–2622. https://doi.org/10.1007/s00521-021-05900-3
7. Ishaq, M., Ping, Q., Haq, Z., Li, C., & Tong, C., (2016). Maximum residue limits and agrifood exports of China: choosing the best estimation technique. Agricultural Economics, 62(2), 78–92. https://doi.org/10.17221/17/2015-agricecon
8. Islam, T., (2016). An empirical estimation of export and import demand functions using bilateral trade data: The case of Bangladesh. Journal of Commerce and Management Thought, 7(3), 526. https://doi.org/10.5958/0976-478x.2016.00030.6

9. 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. https://doi.org/10.3233/sji-210855
10. Sun, M., & Yang, H., (2023). Forecasting model of fishery import and export trade data using deep learning method. 2023 International Conference on Blockchain Technology and Applications (ICBTA).
11. Ahmadpour Kasgari, A., Divsalar, M., Javid, M. R., & Ebrahimian, S. J., (2013). Prediction of bankruptcy Iranian corporations through artificial neural network and Probit-based analyses. Neural Computing & Applications, 23 (3–4), 927–936. https://doi.org/10.1007/s00521-012-1017-z
12. Ko, P., & Lin, P., (2008). Resource allocation neural network in portfolio selection. Expert Systems with Applications, 35(1–2), 330–337. https://doi.org/10.1016/j.eswa.2007.07.031
13. Chang, R.-I., Chiu, Y.-H., & Lin, J.-W., (2020). Two-stage classification of tuberculosis culture diagnosis using convolutional neural network with transfer learning. The Journal of Supercomputing, 76(11), 8641–8656. https://doi.org/10.1007/ s11227-020-03152-x
14. Etebari, F., & Najafi, A. A., (2016). Intelligent choice-based network revenue management. Scientia Iranica, 23(2), 747–756. https://doi.org/10.24200/sci.2016.3860
15. Tsai, C., & Wu, J., (2008). Using neural network ensembles for bankruptcy prediction and credit scoring. Expert Systems with Applications, 34(4), 2639–2649. https://doi.org/10.1016/j.eswa. 2007.05.019
16. Wang, N., Chen, J., Xiao, H., Wu, L., Jiang, H., & Zhou, Y., (2019). Application of artificial neural network model in diagnosis of Alzheimer’s disease. BMC Neurology, 19(1). https://doi.org/ 10.1186/s12883-019-1377-4
17. Alam, T., (2019). Forecasting exports and imports through artificial neural network and autoregressive integrated moving average. Decision Science Letters, 249–260. https://doi.org/ 10.5267/j.dsl.2019.2.001
18. Eşı̇dı̇r, K. A., & Gür, Y. E., (2023). Turkish plastics industry import forecast with artificial neural networks: April-December 2023. The Academic Elegance, 10(23), 91–114. https://doi.org/10.58884/akademik-hassasiyetler.1307536
19. Okkan, U., (2011). Application of Levenberg-Marquardt optimization algorithm based Multilayer Neural Networks for hydrological time series modeling. An International Journal of Optimization and Control Theories & Applications (IJOCTA), 1(1), 53–63. https://doi.org/10.11121/ijocta.01.2011.0038
20. Prasad, V. K., Bhattacharya, P., Bhavsar, M., Verma, A., Tanwar, S., Sharma, G., Bokoro, P. N., & Sharma, R., (2022). ABV-CoViD: An ensemble forecasting model to predict availability of beds and ventilators for COVID-19 like pandemics. IEEE Access: Practical Innovations, Open Solutions, 10, 74131–74151. https://doi.org/ 10.1109/access.2022.3190497
21. Ratnasih, C., & Sulbahri, R. A., (2022). Full Costing Method model and Variable Costing Method against cement price determination (case in Indonesia). European Journal of Business and Management Research, 7(2), 284–288. https://doi.org/10.24018/ ejbmr.2022.7.2.1378
22. Ersen, N., Akyüz, İ., & Bayram, B. Ç., (2019). The forecasting of the exports and imports of paper and paper products of Turkey using Box-Jenkins method. Eurasian Journal of Forest Science, 7(1), 54–65. https://doi.org/10.31195/ejejfs.502397
23. Gür, Y. E., & Eşı̇dı̇r, K. A, (2024). Estimation of turkish trout export with arima and multilayer perceptron models. Turkish Studies-Economy, 19(1), 187–206. https://doi.org/10.7827/ turkishstudies.70444
24. Gür, Y. E., & Eşidir, K. A., (2024). Forecasting Türkiye's paper and paper products sector import using artificial neural networks. Hitit Journal of Social Sciences, 17(2), 206-224. https://doi.org/ 10.17218/hititsbd.1327799
25. Özbek, A., & Akalın, M., (2011). The prediction of Turkey’s denim trousers export to Germany with ANN models. Textile and Apparel, 21(4), 313-322.