高基数欺诈检测中，实体嵌入表现最佳，优于传统编码方法。
Interpretable vs Learned Encoders for High-Cardinality Fraud Detection
- 使用实体嵌入捕捉多列联合特征，提升欺诈识别能力
- 实体嵌入达AUC-ROC 0.9612，显著优于分层编码的0.9548
- 结果对审计友好，适合金融风控场景的可解释性需求
在IEEE-CIS欺诈检测基准数据集（590,540条记录，3.5%正例，8个高基数字段）上测试了七种分类编码方法。采用分层5折交叉验证（重复三次），其中五种编码方法使用相同的冻结LightGBM分类器以确保对比公平。CatBoost和TabNet作为不同范式对照。实体嵌入取得最高AUC-ROC（0.9612），与CatBoost（0.9602）无统计差异，显著优于分层编码（0.9548）。目标编码仅比分层编码低0.0023，且保持审计友好的分层边界。离线版TabNet未超越树模型，在数据稀缺下失效。在AUC-PR上，CatBoost领先（0.822 vs. 0.793），无编码方法同时主导两个指标。逐列分析证实嵌入优势源于多列联合表示能力。
原文摘要 · Abstract (English)
A total of seven categorical encoding methods were tested on the IEEE-CIS fraud benchmark dataset (590,540 records, 3.5% positives, 8 high-cardinality columns). The encoders were evaluated using a stratified 5-fold cross-validation (CV) with three repetitions. Five of the encoders had identical frozen LightGBM learners in the downstream phase, allowing for controlled comparisons of their performance to each other. CatBoost and TabNet were included as comparisons across paradigms using different learners. The entity embeddings produced the highest AUC-ROC (0.9612), with a statistically significant tie with that of CatBoost (0.9602) and statistically superior to tier group encoding (0.9548), whereas target encoding was only 0.0023 worse than tier group encoding and the auditor-friendly tier boundaries were maintained. Off-the-shelf TabNet did not outperform tree-based pipelines and collapsed under data scarcity. On AUC-PR, CatBoost leads (0.822 vs. 0.793); no encoder dominated both metrics. Per-column analysis confirmed the embedding advantage arises from joint multi-column representation.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。