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.
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 Set
ROC-AUC
AP
Transaction-only (T)
0.847
0.537
Graph-only (G)
0.562
0.049
Hybrid (T+G)
0.853
0.537
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 . 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.
Financial fraud detection in transaction networks involves modeling sparse anomalies, dynamic patterns, and severe class imbalance in the presence of temporal drift in the data. In real-world transaction systems, a suspicious transaction is rarely isolated: rather, legitimate and suspicious transactions are often connected through accounts, intermediaries or through temporal transaction sequences. Attribute-based or randomly partitioned learning pipelines are therefore insufficient to detect relationally structured fraud. STC-MixHop, a graph-based framework combining spatial multi-resolution propagation with lightweight temporal consistency modeling for anomaly and fraud detection in dynamic transaction networks. It integrates three components: a MixHop-inspired multi-scale neighborhood diffusion encoder a multi-scale neighborhood diffusion MixHop-based encoder for learning structural patterns; a spatial-temporal attention module coupling current and preceding graph snapshots to stabilize representations; and a temporally informed self-supervised pretraining strategy exploiting unlabeled transaction interactions to improve representation quality. We evaluate the framework primarily on the PaySim dataset under strict chronological splits, supplementing the analysis with Porto Seguro and FEMA data to probe cross-domain component behavior. Results show that STC-MixHop is competitive among graph methods and achieves strong screening-oriented recall under highly imbalanced conditions. The experiments also reveal an important boundary condition: when node attributes are highly informative, tabular baselines remain difficult to outperform. Graph structure contributes most clearly where hidden relational dependencies are operationally important. These findings support a stability-focused view of graph learning for financial fraud detection.
Yiming Lei, Qiannan Shen, Junhao Song
Georgia Institute of Technology, Atlanta, GA, USA · Boston University, Boston, MA, USA · Imperial College London, London, UK
Credit card fraud detection typically relies on tabular features, while repeated attributes can also provide useful relational signals. This paper proposes THGT-FD, a Temporal Heterogeneous Graph Transformer for Fraud Detection. Each transaction is represented using one transaction token and six types of relation tokens and incorporates Time2Vec encoding into the transaction representation. A Transformer learns the interactions among these tokens within each individual transaction and then outputs a fraud probability. Experiments were conducted on 150,000 transactions sampled from the IEEE-CIS Fraud Detection dataset and chronologically partitioned according to TransactionDT. On the test set, THGT-FD achieved an AUC-ROC of 0.8536, an average precision of 0.4164, and a Recall@5% of 0.4708. The class-weighted histogram-based gradient-boosting baseline achieved an AUC-ROC of 0.8722. The results indicate that relation tokens provide useful information for fraud-risk ranking, although the current model does not yet incorporate entity-level historical aggregation.
Qinwen Yan
University of California, Los Angeles Los Angeles, California, USA
Financial transaction fraud prevention faces challenges such as complex relationship structures, concealed behavioral patterns, and dynamically changing data distribution. Discrimination models relying solely on independent sample features are insufficient to fully characterize the risks of group collaboration and chain transfers within transaction networks. This paper proposes a graph neural network representation learning and risk discrimination framework for financial transaction fraud prevention. It integrates transaction records and identity information into node attributes and constructs a transaction graph based on shared attributes and interaction consistency to explicitly model inter-transaction relationships. In model design, a multi-layer message passing mechanism is employed to aggregate neighborhood information, learn node embedding representations containing structural context semantics, and output transaction-level fraud probability and risk scores through a lightweight risk discrimination head. A weighted supervision objective is introduced to mitigate training bias caused by class imbalance, and structural consistency regularization constraints are combined to suppress the impact of noisy edges on representation drift, thereby improving the stability and usability of risk characterization. Experiments are conducted on a publicly available financial transaction dataset, comparing various methods in the same direction and comprehensively evaluating them under a unified evaluation protocol. The results show that the proposed method outperforms other methods in risk ranking and probability calibration quality, validating the effectiveness of graph structure modeling and representation learning collaboration in financial transaction fraud prevention.
Yunfei Nie, Jiawei Wang, Ruobing Yan +3
Brandeis University, Waltham, USA · University of California, Los Angeles, USA · Georgetown University, Washington, D.C., USA +2