AI 中文总结
本研究在受监管信用评分中证明，学习单调循环特征的价值随治理框架严格性上升，且宏观条件化能实现危机队列的AUC提升，确认了框架代价与宏观条件化的必要性。
AI 中文摘要
受监管的信用评分要求每个风险敞口输入的分数单调非递减。已部署的流程——手工构建的单调聚合特征输入到符号约束的梯度提升模型中——已通过组合方式满足这一要求；开放的问题是在此框架内学习时间聚合特征的价值。我们在五个生产规模的信用数据集上，在匹配的可接受性条件下（除一个定价基线约定外），使用单调循环架构进行回答，我们将该架构的逐输入保证通过证明扩展到向量值输入以及外生宏观条件化的衰减门、严重程度、阈值和峰值记忆。由此产生两个发现。第一，严格性阶梯：学习单调特征的价值随治理框架严格性上升——在无约束的工程特征面板上为零，在仅摘要框架中最大——在两个数据集和一个官方时间稳定性指标上得到复现，尽管无条件特征在外部裁决的后续周次上表现退化。第二，制度转移下的条件化传递不对称性。在繁荣期训练、危机期测试的抵押贷款设计上，两个公开宏观经济序列作为输入列有害，但将循环网络的条件化建立在其上，带来了论文中唯一的学习块危机队列提升。确认效应：在内部预注册的Freddie Mac复现中，所有五个保留种子上AUC提升+0.006至+0.013。发现估计：在Fannie Mae上（事后三个种子中的五个）AUC提升+0.015至+0.021，在80%批准阈值下相当于违约余额的10至27个基点，且排除提前预付贷款后增长。州级测试识别了机制：队列间校准转移。疫情带事件限定了范围：在宽限扭曲标签下，该增益在Fannie Mae上以危机规模的四分之一至三分之一泛化，在Freddie Mac上仅对抗容量控制时成立。
英文摘要
Regulated credit scoring requires scores monotone non-decreasing in every exposure input. Deployed pipelines -- hand-crafted monotone aggregates feeding sign-constrained gradient boosting -- already meet this by composition; the open question is what learned temporal aggregation is worth inside one. We answer on five production-scale credit datasets at matched admissibility (one priced baseline convention excepted), with a monotone recurrent architecture whose per-input guarantee we extend, with proofs, to vector-valued inputs and to exogenously macro-conditioned decay gates, severities, thresholds, and peak memory. Two findings result. First, a strictness ladder: the value of learned monotone features rises with governance-frame strictness -- zero on unconstrained engineered panels, maximal in summaries-only frames -- replicated across two datasets and an official temporal-stability metric, though unconditioned features degrade on externally adjudicated later weeks. Second, a conditioning-delivery asymmetry under regime shift. On a train-on-boom, test-on-crisis mortgage design, two public macroeconomic series hurt as input columns, yet conditioning the recurrence on them delivers the paper's only learned-block crisis-cohort uplifts. The confirmed effect: +0.006 to +0.013 AUC on an internally pre-registered Freddie Mac replication, at all five held-out seeds. The discovery estimate: +0.015 to +0.021 on Fannie Mae (three of five seeds post hoc), worth 10-27 basis points of defaulted balance at an 80% approval cutoff, and grows with early-prepaid loans excluded. A state-level test identifies the mechanism: between-cohort calibration transfer. A pandemic-band episode bounds scope: under forbearance-distorted labels the gain generalizes at a quarter to a third of crisis size on Fannie Mae, on Freddie Mac only against the capacity control.
Comments59 pages + 6-page online supplement (ancillary files). Companion to arXiv:2610.05196
