I Trained Six Models for Fraud Detection, and the Best One Isn't in Production
中文摘要
通过欺诈检测项目，作者探讨了评估指标与实际生产决策之间的差距，解释了为何表现最好的模型并未被投入应用。
English Summary
A fraud detection project explores the gap between evaluation metrics and production decisions, explaining why the best-performing model was not deployed.
Original Excerpt
What a final-year project taught me about the gap between evaluation metrics and production decisions The post I Trained Six Models for Fraud Detection, and the Best One Isn't in Production appeared first on Towards Data Science.