The World Customs Organization (WCO) has published a report on “How Artificial Intelligence (AI) can help Customs in automating HS Classification”.
As the awareness among Customs agencies about the importance and the interest in its application grows, the BACUDA expert team, with the support of CCF-Korea, continues to deliver state-of-the-art methods and training material to meet the demands of Members.
Complementing the development of the neural network model to support the classification of goods in Harmonized System, an online advanced Data Analytics course, including a practical module on the HS recommendation algorithm, was published on CLiKC!, the WCO e-learning platform. The BACUDA team of experts collaborated on the development of an AI model to recommend HS codes, which aims to support commodity classification for Customs officials by using historical data to predict HS codes upon the entry of the commercial descriptions of goods.
An accompanying tool provides a demonstration of the functions which the model offers. Upon entering commercial descriptions into the search bar, the corresponding HS codes and their probabilities are given. You can check the recommendations, the corresponding goods descriptions in the nomenclature and statistics on importers, customs agents and exporting countries. It also visualises the functions of the model in a two-dimensional and three-dimensional plane, including the relationship between the HS nomenclature chapters and the recommendation results. A summary of the recommendation is also provided in a separate tab to give an overview of the explicit value it provides.
Overview of the online advanced Data Analytics course
The advanced online course on the model and recommendation service is now available for instant use by Member administrations. The course consists of four chapters that holistically guide the user through all necessary requirements and steps to learn theoretical aspects, train, and evaluate the AI HS algorithm based on Customs data voluntarily provided by the Nigerian Customs Service. You can download the model's source code and experience the referral service first-hand through the online course uploaded to the CLiKC! platform.
Starting with an introduction to the Harmonized System and some practical challenges faced by importers and customs officials, the importance of developing an automated module to support the classification phase in terms of facilitation, resource savings and compliance is highlighted.
The fundamentals of the theory behind the algorithm, including natural language processing and text embedding, are thoroughly explained to supplement the knowledge required to understand the inner workings and derivation of the machine learning model.
A separate course guides the learner step-by-step through the instructions for running the algorithm with Python, pointing out the libraries used, the pre-processing steps required, and how to evaluate the performance of the model.
Finally, the functions and instructions for using the AI HS recommendation service to its full extent are presented in the final chapter of the course.
For further customized support, WCO invites Members to contact WCO BACUDA project team (email@example.com) to organise a joint test of the HS Recommendation AI model with BACUDA experts.