Entity embeddings reach AUC-ROC 0.9612 on IEEE-CIS fraud data, statistically tied with CatBoost and superior to tier group encoding (0.9548), with CatBoost leading on AUC-PR.
Deep learning methods for credit card fraud detection,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Interpretable vs Learned Encoders for High-Cardinality Fraud Detection
Entity embeddings reach AUC-ROC 0.9612 on IEEE-CIS fraud data, statistically tied with CatBoost and superior to tier group encoding (0.9548), with CatBoost leading on AUC-PR.