Customs Fraud Detection in the Presence of Concept Drift

TL;DR

This paper introduces ADAPT, an adaptive method for customs fraud detection that dynamically balances exploration and exploitation to handle concept drift and improve detection accuracy over time.

Contribution

The paper presents ADAPT, a novel adaptive selection approach that adjusts exploration ratios based on model performance and concept drift, enhancing fraud detection in changing trade environments.

Findings

ADAPT effectively adapts to different country datasets.

The optimal exploration ratio varies across countries.

ADAPT maintains high detection performance over time.

Abstract

Capturing the changing trade pattern is critical in customs fraud detection. As new goods are imported and novel frauds arise, a drift-aware fraud detection system is needed to detect both known frauds and unknown frauds within a limited budget. The current paper proposes ADAPT, an adaptive selection method that controls the balance between exploitation and exploration strategies used for customs fraud detection. ADAPT makes use of the model performance trends and the amount of concept drift to determine the best exploration ratio at every time. Experiments on data from four countries over several years show that each country requires a different amount of exploration for maintaining its fraud detection system. We find the system with ADAPT can gradually adapt to the dataset and find the appropriate amount of exploration ratio with high performance.