cs.LGFeb 24, 2026

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

Authors: Hamideh Khaleghpour, Brett McKinney

Organizations: The University of Tulsa, Tulsa, Oklahoma, USA

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

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.

Figures & tables

SplitLicit (0)Illicit (1)
Train ( t≤34t\leq 34 )26,4323,462
Validation ( 35≤t≤4135\leq t\leq 41 )7,154675
Test ( t≥42t\geq 42 )8,433408
Table 1. Temporal split statistics (labeled transactions only).
SplitROC-AUCAP
Validation0.9770.925
Test0.8530.537
Table 2. Random Forest performance on validation and future test sets.
Figure 1. ROC curve on the test set. Receiver operating characteristic curve for the hybrid Random Forest model on the held-out test period, demonstrating discrimination performance across thresholds.
Feature SetROC-AUCAP
Transaction-only (T)0.8470.537
Graph-only (G)0.5620.049
Hybrid (T+G)0.8530.537
Table 3. Feature ablation study on the test set.
Figure 2. Precision–Recall curve on the test set. Precision-Recall curve for the hybrid Random Forest model on the held-out test set, summarizing the trade off between precision and recall under class imbalance.
Figure 3. Test-period confusion matrix at probability threshold =0.80=0.80 . Confusion matrix on the held-out test set at a precision-focused operating threshold of 0.80, illustrating the trade-off between false positives and false negatives.
Figure 4. Calibration curve comparison on the test set for the Random Forest model. Reliability diagrams comparing uncalibrated Random Forest probabilities with sigmoid- and isotonic-calibrated outputs on the held-out test set. The diagonal line represents perfect calibration.
Figure 5. Temporal evolution of the illicit transaction rate across timesteps. Mean illicit label rate per timestep, illustrating class imbalance and temporal distribution shift in the dataset.
Figure 6. Correlation between structural graph features and the illicit transaction label. Pearson correlation coefficients between selected graph-derived features and the binary fraud label, highlighting associations between network structure and illicit behavior.
Figure 7. Top permutation feature importances on the test subset. Permutation importance scores for the top-ranked features, measured as the mean decrease in model performance when each feature is randomly permuted.
Figure 8. Threshold trade-off analysis on the test set. Precision, recall, and F1-score as functions of the decision threshold, illustrating operational trade-offs between detection coverage and alert precision.

Explore similar work

CardsList

  1. A Multi-Scale Graph Learning Framework with Temporal Consistency Constraints for Financial Fraud Detection in Transaction Networks under Non-Stationary Conditions

    Mar 15, 2026Yiming Lei, Qiannan Shen, Junhao SongFinancial Fraud DetectionSpatiotemporal GNNs

    Georgia Institute of Technology, Atlanta, GA, USA · Boston University, Boston, MA, USA · Imperial College London, London, UK

  2. Temporal Heterogeneous Graph Transformer for Credit Card Fraud Detection

    Sep 7, 2026Qinwen YanFinancial Fraud DetectionTransformer

    University of California, Los Angeles Los Angeles, California, USA

  3. Graph-Based Financial Fraud Detection with Calibrated Risk Scoring and Structural Regularization

    May 12, 2026Yunfei Nie, Jiawei Wang, Ruobing Yan +3Graph Neural NetworksGraph Representation Learning

    Brandeis University, Waltham, USA · University of California, Los Angeles, USA · Georgetown University, Washington, D.C., USA +2