METHODS FOR DETERMINING COMMODITY CODES OF GOODS AND VEHICLES ACCORDING TO THE COMMODITY NOMENCLATURE OF FOREIGN ECONOMIC ACTIVITY
Abstract
The article examines traditional and modern methods for determining commodity codes of goods and vehicles according to the Commodity Nomenclature of Foreign Economic Activity (CN FEA). Alongside methods dependent and independent of human factors, an automated classification system based on artificial intelligence technologies – Word2Vec (PV-DBOW model) and logistic regression – is proposed. The model was trained on data from import declarations in the Uzbekistan customs system and demonstrated 85.7% accuracy in test trials. This approach serves to accelerate customs processes, reduce errors, and facilitate the work of specialists.
Keywords
CN FEA, commodity classification, customs control, artificial intelligence, Word2Vec, logistic regression, import declaration, HS code, Harmonized System.
References
- Customs Code of the Republic of Uzbekistan. – Tashkent, 2023.
- Resolution No. 2773 of the State Customs Committee of the Republic of Uzbekistan dated April 6, 2016 “On the Procedure for Filling the Customs Cargo Declaration”.
- World Customs Organization. Harmonized Commodity Description and Coding System. – Brussels, 2022.
- Mikolov T., Sutskever I., Chen K., Corrado G., Dean J. Distributed Representations of Words and Phrases and their Compositionality // Advances in Neural Information Processing Systems. – 2013.
- Jurafsky D., Martin J.H. Speech and Language Processing. – Pearson Education, 2021.
- Géron A. Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow. – O’Reilly Media, 2022.
- Bishop C.M. Pattern Recognition and Machine Learning. – Springer, 2019.