SAGE: Scalable Automatic Gating Ensemble for Confident Negative Harvesting in Fraud Detection

TL;DR

SAGE is a scalable, counterfactual-aware ensemble method for fraud detection in music streaming, effectively identifying negative cases with high confidence despite challenging edge cases.

Contribution

It introduces a novel negative harvesting approach combining stratified sampling with a modular gating ensemble to improve fraud detection accuracy.

Findings

Achieves high precision and recall on held-out data.

Generalizes across different fraud detection domains.

Addresses representation bias in positive-unlabeled learning.

Abstract

Music streaming fraud, where bad actors artificially inflate stream counts to manipulate chart rankings and royalty payments, poses a significant threat to streaming services and legitimate content creators. Traditional fraud detection approaches struggle with a critical challenge: many legitimate edge cases, including super-fans and sleep-music sessions, exhibit activity patterns that closely mimic those of coordinated fraud. We present SAGE, a novel counterfactual-aware negative harvesting approach that combines SimHash-based stratified sampling with a modular gating ensemble for confident negative identification from unlabeled data. Our ensemble architecture employs pluggable statistical gates (currently instantiated with Mahalanobis distance and k-NN density) with configurable voting thresholds enabling adaptive precision-recall trade-offs. This addresses the representation bias problem in Positive-Unlabeled learning by ensuring comprehensive coverage of rare behavioral cohorts through floor-constrained sampling. Evaluation demonstrates strong precision and recall on held-out data. The approach generalizes across fraud detection domains, achieving strong performance on both customer-level and artist-level fraud without modification to the core methodology.