Detalhes bibliográficos
Ano de defesa: |
2024 |
Autor(a) principal: |
Sterrett, Connor Davis |
Orientador(a): |
Não Informado pela instituição |
Banca de defesa: |
Não Informado pela instituição |
Tipo de documento: |
Dissertação
|
Tipo de acesso: |
Acesso aberto |
Idioma: |
eng |
Instituição de defesa: |
Biblioteca Digitais de Teses e Dissertações da USP
|
Programa de Pós-Graduação: |
Não Informado pela instituição
|
Departamento: |
Não Informado pela instituição
|
País: |
Não Informado pela instituição
|
Palavras-chave em Português: |
|
Link de acesso: |
https://www.teses.usp.br/teses/disponiveis/55/55137/tde-29112024-192719/
|
Resumo: |
The Covid-19 pandemic had extensive effects on the economy, significantly disrupting financial health and consumer credit risk. This study examines the impact of the pandemic on consumer loan credit risk, particularly in the rates of delinquency, volume of lending provided to potential borrowers, and changes in attributes which signal credit risk. Data from the peer-to-peer lender LendingClub was analyzed across three periods: before the pandemic, during the peak of the pandemic with lockdowns and government aid, and during the economic recovery phase. Using Information Value and LightGBM techniques, the study compares the predictive power of features across these periods. Key findings include: 1. Reduced Lending Volume: Lending volumes declined substantially during the early pandemic stages. Despite this, loans issued during this period performed well, suggesting that the reduction in lending may have been overly cautious, influenced by government benefits that supported strong credit quality. 2. Increased Delinquencies During Recovery: The post-pandemic recovery period saw significantly higher delinquency rates compared to pre-pandemic levels, highlighting that while creditworthiness remained high during lockdowns and government assistance, the subsequent withdrawal of these supports led to increased financial strain. 3. Shifts in Important Features: During the pandemic, the length of the loan became less significant, whereas the borrowers occupation and geographic location gained importance. This reflects the localized and industry-specific impacts of the pandemic, suggesting that lenders should adjust their risk assessment models to account for these factors in future crises. Understanding these dynamics can help financial institutions and policymakers better prepare for and mitigate the effects of future public health emergencies on consumer credit. |