Modeling Users' Behavior Sequences with Hierarchical Explainable Network for Cross-domain Fraud Detection

TL;DR

This paper introduces a Hierarchical Explainable Network for fraud detection that enhances interpretability and performance, and proposes a transfer framework to adapt models across different e-commerce domains with limited data.

Contribution

The paper presents a novel Hierarchical Explainable Network for interpretable fraud detection and a universal transfer framework for cross-domain adaptation in e-commerce.

Findings

HEN improves fraud detection accuracy and interpretability.

The transfer framework enhances performance in new domains with limited data.

Framework is applicable to various models beyond HEN.

Abstract

With the explosive growth of the e-commerce industry, detecting online transaction fraud in real-world applications has become increasingly important to the development of e-commerce platforms. The sequential behavior history of users provides useful information in differentiating fraudulent payments from regular ones. Recently, some approaches have been proposed to solve this sequence-based fraud detection problem. However, these methods usually suffer from two problems: the prediction results are difficult to explain and the exploitation of the internal information of behaviors is insufficient. To tackle the above two problems, we propose a Hierarchical Explainable Network (HEN) to model users' behavior sequences, which could not only improve the performance of fraud detection but also make the inference process interpretable. Meanwhile, as e-commerce business expands to new domains, e.g., new countries or new markets, one major problem for modeling user behavior in fraud detection systems is the limitation of data collection, e.g., very few data/labels available. Thus, in this paper, we further propose a transfer framework to tackle the cross-domain fraud detection problem, which aims to transfer knowledge from existing domains (source domains) with enough and mature data to improve the performance in the new domain (target domain). Our proposed method is a general transfer framework that could not only be applied upon HEN but also various existing models in the Embedding & MLP paradigm. Based on 90 transfer task experiments, we also demonstrate that our transfer framework could not only contribute to the cross-domain fraud detection task with HEN, but also be universal and expandable for various existing models.