.png){kind=icon}
.png){kind=icon}
Return
DAUNT: Ensemble Disagreement as Actionable Uncertainty for Imbalanced Fraud Detection
.png){kind=icon}
OA
AI
X
G
DOI：10.3390/make8080233.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Detecting a few hundred fraudulent transactions among hundreds of thousands is an extreme class-imbalance problem where one miss can cost a full transaction value. Stacking heterogeneous classifiers is the standard recipe, yet under a leakage-free, precision–recall evaluation, its ranking gain over the best single model is inconsistent: sizable when the base learners are diverse, and negligible when they are redundant. The ensemble’s dependable value lies elsewhere: member disagreement is a usable, threshold-free estimate of epistemic uncertainty. We propose Daunt (Disagreement As UNcertainty for Triage), which turns this disagreement into three deployment layers over one ensemble: (i) routing the most uncertain transactions to human review by ranking them on base-learner disagreement, (ii) deciding alarms by an example-dependent rule that weighs the fraud score against the transaction amount, and (iii) attaching interpretations verified for faithfulness and stability. On two contrasting datasets, the anonymized ULB ( 0.17 % fraud) and feature-rich IEEE-CIS ( 3.5 % fraud), deferring the 5 % most uncertain transactions raises system recall from 0.76 to 0.91 (ULB) and 0.66 to 0.75 (IEEE-CIS) while removing every automated false alarm, and the example-dependent rule recovers more fraudulent money than any global threshold. Daunt reframes the heterogeneous ensemble as a source of actionable uncertainty rather than an end in itself.
Keywords:
fraud detection
class imbalance
ensemble disagreement
uncertainty quantification
selective prediction
cost-sensitive learning
interpretability
Journal
M
IF:
6
Papers:
772
Citations:
1.8K
Organization
Cited Papers