Nov 21, 2022 · Artificial Intelligence

An Adaptive Framework for Confidence-Constraint Rule Set Learning in Large Datasets

The paper introduces a constraint‑adaptive rule‑set learning framework (CRSL) that combines a constraint‑aware decision‑tree miner (CARM), a rule‑sorting filter, and a Bayesian rule‑combination selector (CBRS), achieving superior performance and interpretability on benchmark and massive industrial fraud‑detection data and being deployed in Alipay’s risk‑analysis platform.

Bayesian methodsDecision Treesconstraint optimization

0 likes · 10 min read

An Adaptive Framework for Confidence-Constraint Rule Set Learning in Large Datasets

AntTech

Nov 6, 2022 · Artificial Intelligence

Advanced Rule Learning, Constraint‑Adaptive Frameworks, and Semi‑Supervised Data Augmentation for Fraud Detection and Imbalanced Ranking

This article surveys recent Ant Group research on explainable fraud detection, including constraint‑adaptive rule‑set learning (CRSL), meta‑path guided rule generation (MetaRule), biased sampling for imbalanced ranking, and a semi‑supervised data‑augmentation framework (SDAT) for tabular data, highlighting their motivations, methodologies, deployments, and experimental results.

Semi-supervised Learningconstraint adaptivedata augmentation

0 likes · 18 min read

Advanced Rule Learning, Constraint‑Adaptive Frameworks, and Semi‑Supervised Data Augmentation for Fraud Detection and Imbalanced Ranking