Machine Learning for Detection of Trade in Strategic Goods: An Approach to Support Future Customs Enforcement and Outreach

Abstract

Customs authorities have a critical role in identifying trade in strategic goods that could have an adverse impact on international security. This study proposes a method of using data resampling and the Random Forest machine learning algorithm to model common patterns and characteristics that separate transactions involving strategic goods from broader international trade flows. By embracing advances in machine learning and computing power, customs authorities can leverage existing data to improve enforcement and outreach efforts related to strategic goods subject to international export control regulations.