Conditional Weight of Evidence for Gradient-Boosted Credit Models: Estimation, Additivity and Its Relation to Adverse Action Reasons

arXiv:2610.24586 · stat.ML, cs.LG, q-fin.RM, stat.ME · Submitted 2026-10-17 · Read on arXiv

stat.ML, cs.LG, q-fin.RM, stat.ME

Submitted: 2026-10-17

Updated: 2026-10-17

Comments: 41 pages, 3 figures, 12 tables. Code: https://github.com/asudjianto-xml/GBDT-WoE

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Additivity — 1× in this paper · explained in 1 episode

Related papers

• Behavior of prediction performance metrics with rare events
• Optimal Estimation of Generic Dynamics by Path-Dependent Neural Jump ODEs
• A Posterior-Dynamics Framework for Imaging Inverse Problems with Pretrained Diffusion Priors
• Efficient quadratic entropy with distance sketches
• Embedding-Bias in Conditional Independence Testing
• From Log-Odds to Shapley Values: An Explanatory Geometry for the Weighted Naive Bayes Classifier