Skip to main navigation menu Skip to main content Skip to site footer

MACHINE LEARNING MODELS FOR PREDICTING HS CODE: PROSPECTS AND EFFECTIVENESS OF USE

Affiliation
Head of the Department of the Customs Institute Doctor of Economics, Professor

Abstract

The article examines various machine learning models for predicting GN FEA codes based on product descriptions entered into customs declarations. GN FEA codes are widely used by all customs services due to a number of advantages, including a more convenient and simplified approach to calculating duties and preventing potential revenue loss. This study is based on a cross -industry process to develop a data mining methodology. The results demonstrate that machine learning models are effective tools for predicting GN FEA codes based on input data. 38

Keywords

machine learning, GN FEA codes, predictive models, customs services, revenue loss prevention, trade


References

  1. Che J., Xing Y., Zhang L. A comprehensive solution for deep -learning based cargo inspection to discriminate goods in containers. – IEEE Xplore, 2018. URL: https://www.researchgate.net/publication/329744175_A_Comprehensive_Solution_f or_Deep -Learning_Based_Cargo_Inspection_to_Discriminate_Goods_in_Containers
  2. Ding L., Fan Z., Chen D. Auto -categorization of HS Code using background net approach. // Procedia Computer Science, 2015. – P.1462 -1471. URL: https://www.sciencedirect.com/science/article/pii/S1877050915023510?via%3Dihub
  3. KPMG International: Transforming the tax function through technology, 2018. URL: https://home.kpmg/content/dam/kpmg/au/pdf/2018/transforming -the- taxfunction -au.pdf
  4. Mohammed M., Kha M.B., Bashie E.B. Machine Learning -Algorithms and Applications. // CRC Press, Boca Raton, 2017. URL: https://api.pageplace.de/preview/DT0400.9781498705394_A27230551/preview - 9781498705394_A27230551.pdf
  5. United Nations: Globally Harmonized System of Classification and Labelling of Chemicals (GHS). // 5th Revised ed. United Nations, Geneva, 2013. URL: https://unece.org/DAM/trans/danger/publi/ghs/ghs_rev05/English/ST -SG-AC10 -30- Rev5e.pdf
  6. Youyi W. Exploration of Data -Driven Intelligent Customs, 2017. URL: https://www.eiseverywhere.com/file_uploads/c7e054aa02ad13907d6ad513ea57b8d_s ession3 -YouyiWu.pdf
  7. Zang B., Li Y., Xie W., Chen Z., Tsai C., Laing C. An ontological engineering approach for automating inspection and quarantine at airports. // Journal Computer System Science, №74, 2008. – Р.196 -210. URL: https://www.sciencedirect.com/science/article/pii/S0022000007000499?pes=vor&ut m_source=wiley&getft_integrator=wiley

Downloads

Download data is not yet available.