The prediction of mortgage prepayment risks in the early stages of loan origination: a machine learning approach

Zilong Liu and Hongyan Liang

Journal of Risk

Abstract: This study presents a machine learning model to predict mortgage prepayment risks at the loan origination phase, leveraging variables such as loan-to-value ratios, credit scores and interest rates. The model diverges from traditional postorigination analyses, providing early predictions that are essential for enhancing loan profitability. Our findings reveal that the original interest rate, loan-to-value ratio and borrower credit score are pivotal predictors of prepayment behavior. We also find significant differences in prepayment behavior across bank, nonbank and fintech lenders, emphasizing the need for lender-specific risk assessment strategies. The study demonstrates the importance of origination variables in prepayment predictions, offering financial institutions a tailored approach to risk management.

References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.risk.net/journal-of-risk/7960705/the-p ... ne-learning-approach (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:rsk:journ4:7960705

Access Statistics for this article

More articles in Journal of Risk from Journal of Risk
Bibliographic data for series maintained by Thomas Paine ().