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

Portuguese

As restrições de compartilhamento de dados interinstitucionais tornam este problema particularmente difícil para os pequenos credores com dados de treinamento limitados, forçando os credores a confiar nos rendimentos reportados e, potencialmente, levando à sobre-empréstimos, ofertas excessivamente conservadoras ou rejeição de candidatos credíveis. As restrições de compartilhamento de dados interinstitucionais tornam este problema particularmente difícil para os pequenos credores com dados de treinamento limitados. Introduzimos o FedIncome, um quadro de aprendizagem federado para estimativas de rendimentos padrão que permite às instituições treinar um modelo compartilhado sem agrupar registros de rendimentos brutos centralizados. Usando mais de um milhão de empréstimos do LendingClub divididos em clientes estaduais de US$ 50, simulamos um consórcio de emprés

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