Wells Fargo 用新方法做欺诈检测，误报少于生产级 XGBoost 模型
精选理由
Wells Fargo 讲了怎么把欺诈检测做得比自家 XGBoost 还准，同时少错杀正常付款，做风控的可以看看
Wells Fargo 的 Freddy Lecue 在 AI Engineer New York 大会上分享了该行的欺诈检测进展。对比对象是他们的生产级 XGBoost 模型，新方法在两个指标上同时改善：抓到更多欺诈交易，误拒的正常支付更少。他解释了交易历史数据为何是关键因素。
原文 · AI Engineer
Catch more fraud. Decline fewer legitimate payments. Freddy Lecue of @WellsFargo reports better fraud detection and fewer false positives than their production XGBoost model. His AI Engineer New York clip explains why transaction history matters. #AIEngineerNY Your browser does not support the video tag. 🔗 View on Twitter 💬 0 🔄 0 ❤️ 1 👀 321 ⚡
