| Nome: | Descrição: | Tamanho: | Formato: | |
|---|---|---|---|---|
| 1.51 MB | Adobe PDF |
Autores
Orientador(es)
Resumo(s)
Since the latest global financial crisis there is an increase importance in the role of lending market,
specially by policy interest and bank regulation. In this article it is proposed a methodology to
implement credit risk assessment to estimate the expected credit losses on trade account receivable
for B2B companies as it is required by the new accounting standard CECL (Current Expected Credit
Loss). The EL (Expected Loss) calculation is the multiplication of PD (Probability of default), by LGD
(Loss Given Default) and EAD (Expected at Default). The main focus of this study is the estimation of
probability of default with the use of logistic regression model to a dataset from around 350 companies
in the Automotive Aftermarket Parts sector in Portugal. The model proposed showed the most
significant financial ratios and other qualitative variables in predicting the entities´ credit worthiness
with 86.8% of accuracy, 31.7% of sensitivity and AUC of 74.2%. An additional objective is, with the
model result, support the B2B companies not only comply with CECL but also better assess the
customer’s creditworthiness and therefore develop a sound credit risk policy and management.
Descrição
Dissertation presented as the partial requirement for obtaining a Master's degree in Statistics and Information Management, specialization in Marketing Research and CRM
Palavras-chave
Bad debt Credit risk Trade Receivables Probability of default Scoring
