Newest papers

FedIncome: Federated Learning for Income Estimation in Digital Lending Under Data Sovereignty Constraints

Sultan Amed, Tanmay Sen, Sayantan Banerjee · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2609.27654 · cited by 0 works (OpenAlex) · open-access PDF

Korean

Fed의 검증된 수입은 디지털 데이터 대출 애플리케이션에서 종종 사용할 수 없으며, 대출 기관이 보고된 수입에 의존하도록 강요하여 과도한 대출, 과도하게 보수적 인 제안 또는 신용 할 수있는 신청자의 거부를 초래할 수 있습니다. 통합 데이터 공유 제약은 디지털 데이터 대출 기관에서이 문제를 특히 어렵게 만듭니다. 우리는 FedIncome를 도입합니다. 연방 학습 프레임 워크 (Federated Learning Framework for Income Estimation)는 기관이 합병 된 집중화 된 집중화 된 수입 기준을 위해 $0.619 달러와 비교하여 공유 모델을 훈련 할 수 있습니다. $50 달러 국가 수준의 클라이언트로 분할 수있는 1 백만 달러 이상의

Machine translation (Meta M2M100); the English original follows.

Abstract

Verified income is often unavailable in digital loan applications, forcing lenders to rely on reported income and potentially leading to over-lending, overly conservative offers, or rejection of creditworthy applicants. Cross-institutional data-sharing constraints make this problem especially difficult for smaller lenders with limited training data. We introduce FedIncome, a federated learning framework for income estimation that enables institutions to train a shared model without pooling raw borrower records. Using more than one million LendingClub loans partitioned into $50$ state-level clients, we simulate a heterogeneous lending consortium. The best federated model achieves out-of-time $R^2=0.608$, compared with $0.619$ for a pooled centralised benchmark. Small-sample clients obtain an average out-of-time $R^2$ improvement of $3.8$ percentage points relative to the pooled centralised benchmark, while the fitted client-level relationship places the empirical crossover at approximately $4,790$ training observations in this setting. When pooling is infeasible and the relevant alternative is local-only training, federation improves out-of-time performance across all sample-size groups, with the largest gains for data-scarce clients. We also combine federated income estimates with state- and income-specific debt-to-income thresholds. In a retrospective decision analysis, replacing reported income with the federated estimate increases simulated approval rates with only modest changes in observed default rates. FedIncome supports collaborative learning under data-locality constraints with little aggregate loss relative to pooled training and larger gains relative to local-only estimation.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Pooling, Estimation, Econometrics, Loan, Computer science, Economics

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange