Class imbalance Bayesian model averaging for consumer loan default prediction: The role of soft credit information

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216275%3A25410%2F25%3A39923420" target="_blank" >RIV/00216275:25410/25:39923420 - isvavai.cz</a>

Result on the web

<a href="https://www.sciencedirect.com/science/article/pii/S0275531924005154#ack0005" target="_blank" >https://www.sciencedirect.com/science/article/pii/S0275531924005154#ack0005</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1016/j.ribaf.2024.102722" target="_blank" >10.1016/j.ribaf.2024.102722</a>

Result language

angličtina

Original language name

Class imbalance Bayesian model averaging for consumer loan default prediction: The role of soft credit information

Original language description

This study investigates the predictive value of soft information for consumer loan defaults. We propose a novel framework to address class imbalance by utilizing the concept of Bayesian model averaging. Specifically, we assign unequal weights to machine learning sub-models that incorporate different combinations of variables, thereby creating an accurate and robust model for predicting consumer loan defaults. Additionally, this framework incorporates the Shapley additive explanations (SHAP) method to estimate individual contributions and employs the Bayesian information criterion to assess the variable contributions of the sub-models. We validate the effectiveness and robustness of our proposed method using authentic loan data and publicly available credit default records from a prominent consumer platform in China. Our empirical research suggests that the characteristics of user online behavior are significantly predictive of loan defaults, demonstrating asymmetry at different stages of default.

Czech name

—

Czech description

—

Type

J_imp - Article in a specialist periodical, which is included in the Web of Science database

CEP classification

—

OECD FORD branch

50204 - Business and management

Project

—

Continuities

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Publication year

2025

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Name of the periodical

Research in International Business and Finance

ISSN

0275-5319

e-ISSN

1878-3384

Volume of the periodical

74

Issue of the periodical within the volume

February

Country of publishing house

NL - THE KINGDOM OF THE NETHERLANDS

Number of pages

25

Pages from-to

102722

UT code for WoS article

001402176700001

EID of the result in the Scopus database

2-s2.0-85213264310