Leakage Safe Graph Features for Interpretable Fraud Detection in Temporal Transaction Networks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Khaleghpour, Hamideh, McKinney, Brett
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917319238746112
author Khaleghpour, Hamideh
McKinney, Brett
author_facet Khaleghpour, Hamideh
McKinney, Brett
contents Illicit transaction detection is often driven by transaction level attributes however, fraudulent behavior may also manifest through network structure such as central hubs, high flow intermediaries, and coordinated neighborhoods. This paper presents a time respecting, leakage safe (causal) graph feature extraction protocol for temporal transaction networks and evaluates its utility for illicit entity classification. Using the Elliptic dataset, we construct directed transaction graphs and compute interpretable structural descriptors, including degree statistics, PageRank, HITS hub or authority scores, k-core indices, and neighborhood reachability measures. To prevent look ahead bias, we additionally compute causal variants of graph features using only edges observed up to each timestep. A Random Forest classifier trained with strict temporal splits achieves strong discrimination on a held out future test period (ROC-AUC about 0.85, Average Precision about 0.54). Although transaction attributes remain the dominant predictive signal, graph derived features provide complementary interpretability and enable risk context analysis for investigation workflows. We further assess operational utility using Precision at k and evaluate probability reliability via calibration curves and Brier scores, showing that calibrated models yield better aligned probabilities for triage. Overall, the results support causal graph feature extraction as a practical and interpretable augmentation for temporal fraud detection pipelines.
format Preprint
id arxiv_https___arxiv_org_abs_2603_06632
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Leakage Safe Graph Features for Interpretable Fraud Detection in Temporal Transaction Networks
Khaleghpour, Hamideh
McKinney, Brett
Machine Learning
Cryptography and Security
Illicit transaction detection is often driven by transaction level attributes however, fraudulent behavior may also manifest through network structure such as central hubs, high flow intermediaries, and coordinated neighborhoods. This paper presents a time respecting, leakage safe (causal) graph feature extraction protocol for temporal transaction networks and evaluates its utility for illicit entity classification. Using the Elliptic dataset, we construct directed transaction graphs and compute interpretable structural descriptors, including degree statistics, PageRank, HITS hub or authority scores, k-core indices, and neighborhood reachability measures. To prevent look ahead bias, we additionally compute causal variants of graph features using only edges observed up to each timestep. A Random Forest classifier trained with strict temporal splits achieves strong discrimination on a held out future test period (ROC-AUC about 0.85, Average Precision about 0.54). Although transaction attributes remain the dominant predictive signal, graph derived features provide complementary interpretability and enable risk context analysis for investigation workflows. We further assess operational utility using Precision at k and evaluate probability reliability via calibration curves and Brier scores, showing that calibrated models yield better aligned probabilities for triage. Overall, the results support causal graph feature extraction as a practical and interpretable augmentation for temporal fraud detection pipelines.
title Leakage Safe Graph Features for Interpretable Fraud Detection in Temporal Transaction Networks
topic Machine Learning
Cryptography and Security
url https://arxiv.org/abs/2603.06632