DATE: Dual Attentive Tree-aware Embedding for Customs Fraud Detection

Sundong Kim, Yu Che Tsai, Karandeep Singh, Yeonsoo Choi, Etim Ibok, Cheng Te Li, Meeyoung Cha

研究成果: Conference contribution

25 引文 斯高帕斯(Scopus)

摘要

Intentional manipulation of invoices that lead to undervaluation of trade goods is the most common type of customs fraud to avoid ad valorem duties and taxes. To secure government revenue without interrupting legitimate trade flows, customs administrations around the world strive to develop ways to detect illicit trades. This paper proposes DATE, a model of Dual-task Attentive Tree-aware Embedding, to classify and rank illegal trade flows that contribute the most to the overall customs revenue when caught. The strength of DATE comes from combining a tree-based model for interpretability and transaction-level embeddings with dual attention mechanisms. To accurately identify illicit transactions and predict tax revenue, DATE learns simultaneously from illicitness and surtax of each transaction. With a five-year amount of customs import data with a test illicit ratio of 2.24%, DATE shows a remarkable precision of 92.7% on illegal cases and a recall of 49.3% on revenue after inspecting only 1% of all trade flows. We also discuss issues on deploying DATE in Nigeria Customs Service, in collaboration with the World Customs Organization.

原文English
主出版物標題KDD 2020 - Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
發行者Association for Computing Machinery
頁面2880-2890
頁數11
ISBN(電子)9781450379984
DOIs
出版狀態Published - 2020 8月 23
事件26th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2020 - Virtual, Online, United States
持續時間: 2020 8月 232020 8月 27

出版系列

名字Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining

Conference

Conference26th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2020
國家/地區United States
城市Virtual, Online
期間20-08-2320-08-27

All Science Journal Classification (ASJC) codes

  • 軟體
  • 資訊系統

指紋

深入研究「DATE: Dual Attentive Tree-aware Embedding for Customs Fraud Detection」主題。共同形成了獨特的指紋。

引用此