Reproduce “Reconstructing Fraudulent Strategies in Online Payments via Interpretable Inverse Reinforcement Learning” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Huilin He, Weiyu Han, Linbo Shao, Ruobing Zuo, Xiao Tan, Shuai Chen, Dawei Cheng
PaySeqGen generates fraud-detector training sequences by learning how next-payment choices depend on transaction history and outcomes. It combines history-guided and exploratory candidates, learns interpretable rewards with feedback–action interactions, and alternates reward learning with policy optimization. Offline, augmentation raised the production detector’s Recall@2 by 1.621 percentage points over baseline; gains varied, with XGBoost Recall@2 changing −0.047 points.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.