Tag
Introduces SAGE, the first end-to-end LLM-driven multi-agent framework for fraud detection, using a Data Diagnostic Tree and Markov decision process with natural-language gradients to optimize models under class imbalance. Experiments show significant F1 improvements over baselines across five datasets.
Silicon Valley titan Peter Thiel shares PayPal's early experience of being on the verge of bankruptcy due to fraud, and how it got out of trouble through human-machine collaboration (computer screening + human qualitative investigation), pointing out that this collaborative paradigm is underestimated by the AI research community.
Financial institutions are shifting from siloed AI models to unified transaction foundation models built on transformer architectures, as demonstrated by NVIDIA's report and Revolut's PRAGMA model, which improves fraud detection, credit scoring, and recommendations while reducing feature engineering effort.
SilIF augments Isolation Forest with a silhouette-based scoring layer on per-tree path length fingerprints, improving unsupervised transaction fraud detection on the IEEE-CIS benchmark by +0.0080 AUC-PR on average.
A merchant details a case of friendly fraud where Stripe refused to use clear evidence of abuse to improve its cross-merchant fraud detection, despite marketing its Radar product on network-wide signals.
This survey examines computational nondeterminism in financial AI systems, covering tabular models, graph networks, and LLM-based workflows, and proposes a layered evaluation framework for auditability.
ORACLE is a new agentic framework for early scam anticipation from streaming app usage trajectories. It uses a self-evolving context manager and on-policy self-distillation to detect scams from partial observations over multiple apps and days.
A practical guide to six SQL patterns for detecting transaction fraud in financial data, including velocity checks, impossible travel detection, and other methods. The author shares real-world examples and tuning advice.
This paper evaluates LLM-based simulators as generators of differentially private synthetic data, using PersonaLedger to assess whether LLMs can faithfully reproduce statistical distributions from DP-protected personas. While achieving promising fraud detection utility (AUC 0.70 at ε=1), the study identifies significant distribution drift caused by systematic LLM biases that override input statistics.
SafetyKit launches AI agents powered by OpenAI's GPT-5, GPT-4.1, and specialized techniques to detect fraud and prohibited activity across text, images, and financial transactions with 95%+ accuracy. The solution enables marketplaces and fintech platforms to automate risk detection, policy enforcement, and content moderation at scale.
Stripe deployed GPT-4 across multiple workflows including support customization, developer documentation assistance, and fraud/bad-actor detection in Discord communities, finding the model outperformed human reviewers in several tasks. The company ran an internal hackathon-style initiative with 100 employees to identify and prototype AI-powered features using OpenAI's latest models.