Research Article
BibTex RIS Cite

Gümrük Kontrol Noktalarında Riskli Geçişlerin Belirlenmesine Yönelik Yapay Zekâ Temelli Bir Yaklaşım

Year 2024, Volume: 14 Issue: 2, 476 - 492, 18.06.2024
https://doi.org/10.31466/kfbd.1367857

Abstract

Gelişen teknoloji ve küreselleşmeyle birlikte ülkeler arasında insan ve ürün açısından giriş çıkışlar artmaya başlamıştır. Bu geçişlerde, ürünlerin ülkeler arasında aktarılması ile oluşan dış ticaret işlemlerinde ülkelerin belirli bölgelerinde yer alan sınır kapıları büyük önem taşımaktadır. Mal giriş çıkışının yapıldığı sınır kapıları gümrük olarak adlandırılmakta ve geçecek ürüne göre takip edilen süreçler farklılaşabilmektedir. Türkiye’de ise süreçlerin kontrol edilebilmesi için gümrük noktalarında üç farklı hat kullanılmaktadır: kırmızı hat, sarı hat ve mavi hat. Kırmızı ve mavi hatlarda sırasıyla istisnasız tüm ürünler kontrol edilmekte ya da yetkilendirilmiş kişi sertifikasına sahip olanlar için kontrolsüz geçiş hakkı sağlanmaktadır. Sarı hatlarda ise ürünler gümrük memuru tarafından mevzuat ve yönergeye göre riskli ya da risksiz olarak sınıflandırılmakta ve bu sınıflandırma sonucuna göre gelen mallar kontrol edilmekte ya da edilmemektedir. Yapılan bu çalışmada sarı hat için ürünlerin riskli ya da risksiz olduğunu belirleyebilmek amacıyla makine öğrenmesi ve yapay sinir ağları yöntemleri kullanılarak model geliştirilecektir. Bu doğrultuda makine öğrenmesi başlığı altında yer alan k-en yakın komşu, lojistik regresyon, destek vektör makineleri, karar ağaçları, rassal orman ve naif Bayes yöntemleri ve yapay sinir ağları başlığı altında yer alan çok katmanlı algılayıcı (multi layer perceptron-MLP) yöntemi kullanılmıştır. Elde edilen sonuçlar incelendiğinde karar ağacı yönteminin mevcut veri seti için en iyi sonuçları verdiği gözlemlenmiştir.

References

  • Aborisade, O., Anwar, M., (2018). Classification for Authorship of Tweets by Comparing Logistic Regression and Naive Bayes Classifiers.IEEE International Conference on Information Reuse and Integration (IRI), Salt Lake City, UT, USA, 2018, 269-276
  • Akbıyık, A., & Arı, O. (2022). Lojistik Regresyon İle Faydalı Müşteri Yorumlarını Tahminleme. Journal of Research in Business, 7 (IMISC 2021 Special Issue), 15-32.
  • Alan A., & Karabatak, M. (2020). Veri Seti-Sınıflandırma İlişkisinde Performansa Etki Eden Faktörlerin Değerlendirilmesi. Fırat Üniversitesi Mühendislik Bilimleri Dergisi, 32(2), 531-540.
  • Alpaydin, E. (2020). Introduction to machine learning. MIT press.
  • Bauder, R. A., & Khoshgoftaar, T. M. (2017, December). Medicare fraud detection using machine learning methods. In 2017 16th IEEE international conference on machine learning and applications (ICMLA) (pp. 858-865). IEEE.
  • Dong, S. (2022, January). Virtual currency price prediction based on segmented integrated learning. In 2022 IEEE 2nd International Conference on Power, Electronics and Computer Applications (ICPECA) (pp. 549-552). IEEE.
  • Dornadula, V. N., & Geetha, S. (2019). Credit card fraud detection using machine learning algorithms. Procedia computer science, 165, 631-641.
  • Gardner, M. W., & Dorling, S. R. (1998). Artificial neural networks (the multilayer perceptron) a review of applications in the atmospheric sciences. Atmospheric environment, 32(14-15), 2627-2636.
  • Gümrük İşlemleri, Erişim Tarihi: 02.01.2023, https://ticaret.gov.tr/gumruk-islemleri/sikca-sorulan-sorular/ticari/gumruk-islemleri
  • Hatipler, M. (2011). Türkiye AB Gümrük Birliği Antlaşması ve Antlaşmanın Türkiye Ekonomisine Etkileri, Trakya Üniversitesi Sosyal Bilimler Dergisi, 13(1), 14-32.
  • Jadhav, S. D., & Channe, H. P. (2016). Comparative study of K-NN, naive Bayes and decision tree classification techniques. International Journal of Science and Research (IJSR), 5(1), 1842-1845.
  • James, G., Witten, D., Hastie, T., & Tibshirani, R. (2013). An introduction to statistical learning (Vol. 112, p. 18). New York: springer.
  • Johnson, J. M., & Khoshgoftaar, T. M. (2019). Medicare fraud detection using neural networks. Journal of Big Data, 6(1), 1-35.
  • Li, X. ve Yu, W. (2011). Fast Support Vector Machine Classification for Large Data Sets. International Journal of Computational Intelligence Systems 7(2), 197-212.
  • Maniraj, S. P., Saini, A., Ahmed, S., & Sarkar, S. (2019). Credit card fraud detection using machine learning and data science. International Journal of Engineering Research, 8(9), 110-115.
  • Pattanayak, S., Loha, C., Hauchhum, L., Sailo, L, (2021). Application of MLP-ANN Models for Estimating the Higher Heating Value of Bamboo Biomass, Biomass Conversion and Biorefinery 11, 2499–2508.
  • Perols, J. (2011). Financial statement fraud detection: An analysis of statistical and machine learning algorithms. Auditing: A Journal of Practice & Theory, 30(2), 19-50.
  • Shah, K., Patel, H., Sanghvi, D., Shah, M., (2020). A Comparative Analysis of Logistic Regression, Random Forest and KNN Models for the Text Classification. Augment Hum Res 5, 12
  • Stephens, C.R., Huerta, H.F. & Linares, A.R., (2018). When is the Naive Bayes approximation not so naive?. Mach Learn 107, 397–441.
  • Thennakoon, A., Bhagyani, C., Premadasa, S., Mihiranga, S., & Kuruwitaarachchi, N. (2019, January). Real-time credit card fraud detection using machine learning. In 2019 9th International Conference on Cloud Computing, Data Science & Engineering (Confluence) (pp. 488-493). IEEE.
  • Türkiye’nin Sınır Kapıları (Gümrükler), Erişim Tarihi: 02.01.2023, https://www.tarihselbilgi.com/sinir-kapilari/
  • Xiong L., Yao, Y. (2021). Study on an adaptive thermal comfort model with K-nearest-neighbors (KNN) algorithm. Building and Environment, 202,108026

An Artificial Intelligence Based Approach to Identify Risky Passes at Customs Control Points

Year 2024, Volume: 14 Issue: 2, 476 - 492, 18.06.2024
https://doi.org/10.31466/kfbd.1367857

Abstract

With the developing technology and globalization, the entrances and exits of people and products between countries have begun to increase. Border gates located in some certain areas of the countries have great importance in foreign trade transactions that occur by transferring products between countries during these transitions. Border gates where goods are entered and exited are called customs and the processes followed can be differ according to the product to be passed. In Turkey, three different lines are used at customs points to control the processes: red, yellow, and blue. On the red and blue lines, respectively, all products are controlled without exception or the right of uncontrolled passage is provided for those with an authorized person certificate. On the yellow lines, on the other hand, the products are classified as risky or risk-free by the customs officer according to the legislation and directive, and the incoming goods are controlled or not according to the results of this classification. In this study, a model will be developed for the yellow line using machine learning (ML) and artificial neural network (ANN) methods in order to determine whether the products are risky or risk-free. In this direction, k-nearest neighbor, logistic regression, support vector machines, decision trees, random forest, and naive Bayes methods under the ML title and multi-layer perceptron (MLP) method under the ANN title were used. When the results were examined, it was observed that the decision tree method gave the best results for the existing data set.

References

  • Aborisade, O., Anwar, M., (2018). Classification for Authorship of Tweets by Comparing Logistic Regression and Naive Bayes Classifiers.IEEE International Conference on Information Reuse and Integration (IRI), Salt Lake City, UT, USA, 2018, 269-276
  • Akbıyık, A., & Arı, O. (2022). Lojistik Regresyon İle Faydalı Müşteri Yorumlarını Tahminleme. Journal of Research in Business, 7 (IMISC 2021 Special Issue), 15-32.
  • Alan A., & Karabatak, M. (2020). Veri Seti-Sınıflandırma İlişkisinde Performansa Etki Eden Faktörlerin Değerlendirilmesi. Fırat Üniversitesi Mühendislik Bilimleri Dergisi, 32(2), 531-540.
  • Alpaydin, E. (2020). Introduction to machine learning. MIT press.
  • Bauder, R. A., & Khoshgoftaar, T. M. (2017, December). Medicare fraud detection using machine learning methods. In 2017 16th IEEE international conference on machine learning and applications (ICMLA) (pp. 858-865). IEEE.
  • Dong, S. (2022, January). Virtual currency price prediction based on segmented integrated learning. In 2022 IEEE 2nd International Conference on Power, Electronics and Computer Applications (ICPECA) (pp. 549-552). IEEE.
  • Dornadula, V. N., & Geetha, S. (2019). Credit card fraud detection using machine learning algorithms. Procedia computer science, 165, 631-641.
  • Gardner, M. W., & Dorling, S. R. (1998). Artificial neural networks (the multilayer perceptron) a review of applications in the atmospheric sciences. Atmospheric environment, 32(14-15), 2627-2636.
  • Gümrük İşlemleri, Erişim Tarihi: 02.01.2023, https://ticaret.gov.tr/gumruk-islemleri/sikca-sorulan-sorular/ticari/gumruk-islemleri
  • Hatipler, M. (2011). Türkiye AB Gümrük Birliği Antlaşması ve Antlaşmanın Türkiye Ekonomisine Etkileri, Trakya Üniversitesi Sosyal Bilimler Dergisi, 13(1), 14-32.
  • Jadhav, S. D., & Channe, H. P. (2016). Comparative study of K-NN, naive Bayes and decision tree classification techniques. International Journal of Science and Research (IJSR), 5(1), 1842-1845.
  • James, G., Witten, D., Hastie, T., & Tibshirani, R. (2013). An introduction to statistical learning (Vol. 112, p. 18). New York: springer.
  • Johnson, J. M., & Khoshgoftaar, T. M. (2019). Medicare fraud detection using neural networks. Journal of Big Data, 6(1), 1-35.
  • Li, X. ve Yu, W. (2011). Fast Support Vector Machine Classification for Large Data Sets. International Journal of Computational Intelligence Systems 7(2), 197-212.
  • Maniraj, S. P., Saini, A., Ahmed, S., & Sarkar, S. (2019). Credit card fraud detection using machine learning and data science. International Journal of Engineering Research, 8(9), 110-115.
  • Pattanayak, S., Loha, C., Hauchhum, L., Sailo, L, (2021). Application of MLP-ANN Models for Estimating the Higher Heating Value of Bamboo Biomass, Biomass Conversion and Biorefinery 11, 2499–2508.
  • Perols, J. (2011). Financial statement fraud detection: An analysis of statistical and machine learning algorithms. Auditing: A Journal of Practice & Theory, 30(2), 19-50.
  • Shah, K., Patel, H., Sanghvi, D., Shah, M., (2020). A Comparative Analysis of Logistic Regression, Random Forest and KNN Models for the Text Classification. Augment Hum Res 5, 12
  • Stephens, C.R., Huerta, H.F. & Linares, A.R., (2018). When is the Naive Bayes approximation not so naive?. Mach Learn 107, 397–441.
  • Thennakoon, A., Bhagyani, C., Premadasa, S., Mihiranga, S., & Kuruwitaarachchi, N. (2019, January). Real-time credit card fraud detection using machine learning. In 2019 9th International Conference on Cloud Computing, Data Science & Engineering (Confluence) (pp. 488-493). IEEE.
  • Türkiye’nin Sınır Kapıları (Gümrükler), Erişim Tarihi: 02.01.2023, https://www.tarihselbilgi.com/sinir-kapilari/
  • Xiong L., Yao, Y. (2021). Study on an adaptive thermal comfort model with K-nearest-neighbors (KNN) algorithm. Building and Environment, 202,108026
There are 22 citations in total.

Details

Primary Language Turkish
Subjects Industrial Engineering
Journal Section Articles
Authors

Ezgi Zehra Şeker 0000-0002-8232-0897

Ebru Geçici 0000-0002-7954-9578

Alev Taşkın 0000-0003-1803-9408

Publication Date June 18, 2024
Published in Issue Year 2024 Volume: 14 Issue: 2

Cite

APA Şeker, E. Z., Geçici, E., & Taşkın, A. (2024). Gümrük Kontrol Noktalarında Riskli Geçişlerin Belirlenmesine Yönelik Yapay Zekâ Temelli Bir Yaklaşım. Karadeniz Fen Bilimleri Dergisi, 14(2), 476-492. https://doi.org/10.31466/kfbd.1367857