Rule anchored graph learning improves synthetic identity fraud detection through multi relation structure rather than score level fusion

Abstract

Synthetic Identity Fraud (SIF), in which fraudsters combine real and fabricated information to create untraceable identities, is a fast-growing and costly problem in payment systems. Prior work treats graph neural networks as an assumed improvement over transparent rule-based identity-linkage scoring, but rarely tests where, if anywhere, that improvement originates. We build a heterogeneous Client-SSN-Email-Phone graph from a PaySim-derived identity linkage dataset (2,433 profiles, 433 fraudulent) and compare rule-based, non-graph machine learning, non-deep propagation, and deep graph models across five identity-noise levels and four random seeds. A rule-anchored hybrid combining the rule score with a Heterogeneous Graph Transformer (HGT) and support vector machine (Rule + HGT+SVM) achieves the best average Precision-Recall Area Under the Curve (PR-AUC) of 0.835, versus 0.777 for Rule-only, with a positive difference across all 20 seed-noise combinations tested. Because rule and graph scores rank clients almost identically, we test whether two more sophisticated fusion mechanisms, an adaptive per-client weight and a tie-breaking scheme, can extract further gains; although reordering tied rule scores can in principle affect rank-based metrics, neither mechanism produced consistent gains over the simple fixed fusion, since 99.5% of clients share their rule score with another client. A relation-level ablation instead shows the graph’s value is structural: removing SSN, Email, or Phone individually from the graph consistently reduces average performance across all tested seed-noise configurations, and a density-matched control confirms this is not merely a graph-sparsity artifact (nominal p ≤ 0.0007 for all three in the descriptive 20-pair comparison). What matters is having some relations represented completely rather than all relations represented but thinned. These results show where graph learning’s contribution actually comes from in SIF detection: not from how a fused score is weighted, but from the completeness of the identity relations the encoder can access. Transparent rule-based scoring remains the necessary backbone of a defensible detection pipeline. Fixed fusion preserves rule ordering for 100% of pairs with different rule scores Adaptive and tie-breaking score fusion both fail to beat a simple fixed-weight hybrid Rule-anchored Rule + HGT+SVM improves over rule-only across all 20 seed-noise combinations (PR-AUC 0.835 vs. 0.777) Removing any single identity relation consistently reduces HGT + SVM performance Relation completeness matters more than which specific identity relation is present Fixed fusion preserves rule ordering for 100% of pairs with different rule scores Adaptive and tie-breaking score fusion both fail to beat a simple fixed-weight hybrid Rule-anchored Rule + HGT+SVM improves over rule-only across all 20 seed-noise combinations (PR-AUC 0.835 vs. 0.777) Removing any single identity relation consistently reduces HGT + SVM performance Relation completeness matters more than which specific identity relation is present