Finding NeMo: Fishing in banking networks using network motifs

TL;DR

This paper investigates the use of network motifs in heterogeneous banking transaction graphs to uncover fraud patterns, introducing a new randomization process for realistic graph analysis.

Contribution

It presents a novel approach to analyze banking networks using heterogeneous network motifs and a new graph randomization method for fraud detection.

Findings

Network motifs reveal insightful transaction patterns.

Heterogeneous motifs improve interpretability.

Proposed randomization preserves graph validity.

Abstract

Banking fraud causes billion-dollar losses for banks worldwide. In fraud detection, graphs help understand complex transaction patterns and discovering new fraud schemes. This work explores graph patterns in a real-world transaction dataset by extracting and analyzing its network motifs. Since banking graphs are heterogeneous, we focus on heterogeneous network motifs. Additionally, we propose a novel network randomization process that generates valid banking graphs. From our exploratory analysis, we conclude that network motifs extract insightful and interpretable patterns.