Budgeted Class-Balanced Drift Gating for Directional Temporal Graph Fraud Detection
Journal of Mathematical Finance and Risk Management · 04.11.2026 · 2 (1) · 1-9
DOI: 10.54097/22nqrt47 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Mathematical Finance and Risk Management, online erschienen am 04.11.2026. Verfasst von Sabrina Chandra und 2 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
Concept drift can render a graph-based fraud classifier obsolete even when its topology encoder remains useful. This study investigates when a delayed-label alarm should update a classifier under independent class-prior fluctuations and abrupt changes in transaction-flow roles. Building on the seven-channel directed two-hop simplified graph convolution and stable–plastic classifier of ATGNN-SP, we introduce BCG-5: a class-balanced predictive-loss gate, a five-update stream budget, and recent-only plastic fitting. Controlled experiments use reproducibly generated directed transaction graphs, 49 chronological snapshots, and five paired seeds in three regimes; no production transaction data are used. In the mixed regime, BCG-5 achieves average precision 0.3175 ± 0.0366 and F1 0.3413 ± 0.0693, compared with 0.3004 ± 0.0280 and 0.3367 ± 0.0712 for the loss-gated ATGNN-SP update rule, while reducing mean updates from 8.0 to 5.0. A plastic-only alternative achieves higher predictive accuracy at greater update frequency, revealing a meaningful stability–adaptability trade-off.
Zitieren
APA
Chandra, S., Klein, Y., & Kim, D. (2026). Budgeted Class-Balanced Drift Gating for Directional Temporal Graph Fraud Detection. Journal of Mathematical Finance and Risk Management, 2(1), 1-9. https://doi.org/10.54097/22nqrt47
Vancouver
Chandra S, Klein Y, Kim D. Budgeted Class-Balanced Drift Gating for Directional Temporal Graph Fraud Detection. Journal of Mathematical Finance and Risk Management. 2026;2(1):1-9. doi:10.54097/22nqrt47
BibTeX
@article{Chandra2026,
author = {Chandra, Sabrina and Klein, Yuna and Kim, Diego},
title = {Budgeted Class-Balanced Drift Gating for Directional Temporal Graph Fraud Detection},
journal = {Journal of Mathematical Finance and Risk Management},
year = {2026},
volume = {2},
number = {1},
pages = {1--9},
doi = {10.54097/22nqrt47}
}
EUVIMED