Depicting Risk Profile over Time: A Novel Multiperiod Loan Default Prediction Approach

In stock

Publication History

Received: April 1, 2021
Revised: December 25, 2021; July 21, 2022; November 21, 2022
Accepted: November 29, 2022
Published Online as Articles in Advance: November 30, 2023
Published Online in Issue: December 1, 2023

Downloadable File

With the rapid development of fintech, the need for dynamic credit risk evaluation is becoming increasingly important. While previous studies on credit scoring have mostly focused on single-period loan default prediction, we call for a new avenue—multiperiod default prediction (MPDP)—to depict risk profiles over time. To address the challenges raised by MPDP, such as monotonic default probability prediction and complex relationship accommodation, we propose a novel approach, hybrid and collective scoring (HACS). We design a hybrid modeling strategy to predict whether and when a borrower will default separately through a default discrimination model and a default time estimation model, respectively, and synthesize them through a probabilistic framework. To accommodate various possible patterns of default time and measure the distribution of default probability over successive time intervals, we propose a joint default modeling method to train the default time estimation model. Empirical evaluations at the model (time-to-default prediction performance and discrimination performance) and mechanism (identifiability and discriminability) levels, as well as impact analyses at the application (granting performance and profitability performance) level, show that HACS outperforms the benchmarked survival analysis and multilabel learning methods on all fronts. It can more accurately predict time-to-default and provide financial institutions and investors better decision-support in granting loans and selecting loan portfolios.

Additional Details
Author Zhao Wang, Cuiqing Jiang, and Huimin Zhao
Year 2023
Volume 47
Issue 4
Keywords Credit risk, dynamic evaluation, multiperiod default prediction, hybrid modeling, monotonic probability, risk analysis, profit scoring
Page Numbers 1455-1486
Copyright © 2023 MISQ. All rights reserved.