Do Fintech Lenders Align Pricing with Risk? Evidence from a Model-Based Assessment of Conforming Mortgages

This paper assesses whether fintech mortgage lenders align pricing with borrower risk using conforming 30-year mortgages (2012–2020). We estimate default probabilities using machine learning (logit, random forest, gradient boosting, LightGBM, XGBoost), finding that non-fintech lenders achieve the hi...

Full description

Saved in:
Bibliographic Details
Main Authors: Zilong Liu, Hongyan Liang
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:FinTech
Subjects:
Online Access:https://www.mdpi.com/2674-1032/4/2/23
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849432637812244480
author Zilong Liu
Hongyan Liang
author_facet Zilong Liu
Hongyan Liang
author_sort Zilong Liu
collection DOAJ
description This paper assesses whether fintech mortgage lenders align pricing with borrower risk using conforming 30-year mortgages (2012–2020). We estimate default probabilities using machine learning (logit, random forest, gradient boosting, LightGBM, XGBoost), finding that non-fintech lenders achieve the highest predictive accuracy (AUC = 0.860), followed closely by banks (0.857), with fintech lenders trailing (0.852). In pricing analysis, banks adjust the origination rates most sharply with borrower risk (7.20 basis points per percentage-point increase in default probability) compared to fintech (4.18 bp) and non-fintech lenders (5.43 bp). Fintechs underprice 32% of high-risk loans, highlighting limited incentive alignment under GSE securitization structures. Expanding the allowable alternative data and modest risk-retention policies could enhance fintechs’ analytical effectiveness in mortgage markets.
format Article
id doaj-art-50b4f990cd3c4e63bca30d863532822f
institution Kabale University
issn 2674-1032
language English
publishDate 2025-06-01
publisher MDPI AG
record_format Article
series FinTech
spelling doaj-art-50b4f990cd3c4e63bca30d863532822f2025-08-20T03:27:18ZengMDPI AGFinTech2674-10322025-06-01422310.3390/fintech4020023Do Fintech Lenders Align Pricing with Risk? Evidence from a Model-Based Assessment of Conforming MortgagesZilong Liu0Hongyan Liang1Gies College of Business, University of Illinois Urbana-Champaign, Urbana, IL 61801, USAGies College of Business, University of Illinois Urbana-Champaign, Urbana, IL 61801, USAThis paper assesses whether fintech mortgage lenders align pricing with borrower risk using conforming 30-year mortgages (2012–2020). We estimate default probabilities using machine learning (logit, random forest, gradient boosting, LightGBM, XGBoost), finding that non-fintech lenders achieve the highest predictive accuracy (AUC = 0.860), followed closely by banks (0.857), with fintech lenders trailing (0.852). In pricing analysis, banks adjust the origination rates most sharply with borrower risk (7.20 basis points per percentage-point increase in default probability) compared to fintech (4.18 bp) and non-fintech lenders (5.43 bp). Fintechs underprice 32% of high-risk loans, highlighting limited incentive alignment under GSE securitization structures. Expanding the allowable alternative data and modest risk-retention policies could enhance fintechs’ analytical effectiveness in mortgage markets.https://www.mdpi.com/2674-1032/4/2/23fintech mortgage lendingrisk-based pricingdefault predictionmachine learningcredit risk modeling
spellingShingle Zilong Liu
Hongyan Liang
Do Fintech Lenders Align Pricing with Risk? Evidence from a Model-Based Assessment of Conforming Mortgages
FinTech
fintech mortgage lending
risk-based pricing
default prediction
machine learning
credit risk modeling
title Do Fintech Lenders Align Pricing with Risk? Evidence from a Model-Based Assessment of Conforming Mortgages
title_full Do Fintech Lenders Align Pricing with Risk? Evidence from a Model-Based Assessment of Conforming Mortgages
title_fullStr Do Fintech Lenders Align Pricing with Risk? Evidence from a Model-Based Assessment of Conforming Mortgages
title_full_unstemmed Do Fintech Lenders Align Pricing with Risk? Evidence from a Model-Based Assessment of Conforming Mortgages
title_short Do Fintech Lenders Align Pricing with Risk? Evidence from a Model-Based Assessment of Conforming Mortgages
title_sort do fintech lenders align pricing with risk evidence from a model based assessment of conforming mortgages
topic fintech mortgage lending
risk-based pricing
default prediction
machine learning
credit risk modeling
url https://www.mdpi.com/2674-1032/4/2/23
work_keys_str_mv AT zilongliu dofintechlendersalignpricingwithriskevidencefromamodelbasedassessmentofconformingmortgages
AT hongyanliang dofintechlendersalignpricingwithriskevidencefromamodelbasedassessmentofconformingmortgages