Customs Fraud Detection in the Presence of Concept Drift

09/29/2021
by   Tung-Duong Mai, et al.
0

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.

READ FULL TEXT
research
03/09/2022

Autoregressive based Drift Detection Method

In the classic machine learning framework, models are trained on histori...
research
07/25/2017

Concept Drift Detection and Adaptation with Hierarchical Hypothesis Testing

In a streaming environment, there is often a need for statistical predic...
research
06/07/2021

MemStream: Memory-Based Anomaly Detection in Multi-Aspect Streams with Concept Drift

Given a stream of entries over time in a multi-aspect data setting where...
research
02/05/2001

Self-adaptive exploration in evolutionary search

We address a primary question of computational as well as biological res...
research
04/19/2023

Advances on Concept Drift Detection in Regression Tasks using Social Networks Theory

Mining data streams is one of the main studies in machine learning area ...
research
01/20/2023

Feature Relevance Analysis to Explain Concept Drift – A Case Study in Human Activity Recognition

This article studies how to detect and explain concept drift. Human acti...
research
06/15/2022

Learn to Adapt: Robust Drift Detection in Security Domain

Deploying robust machine learning models has to account for concept drif...

Please sign up or login with your details

Forgot password? Click here to reset