Models that improve most from added country and behaviour features also show larger path-specific fairness violations on synthetic AML data, illustrating an accuracy–fairness trade-off.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Counterfactual Methods for Detecting Unfairness in Anti-Money Laundering Algorithms
Models that improve most from added country and behaviour features also show larger path-specific fairness violations on synthetic AML data, illustrating an accuracy–fairness trade-off.