Credit Risk Scoring: A Stacking Generalization Approach

Research output: Chapter in Book/Report/Conference proceedingChapterpeer-review

Abstract

Forecasting the creditworthiness of customers in new and existing loan contracts is a central issue of lenders’ activity. Credit scoring involves the use of analytical methods to transform historical loan application and loan performance data into credit scores that signal creditworthiness, inform, and determine credit decisions, determine credit limits, and loan rates, and assist in fraud detection, delinquency intervention, or loss mitigation. The standard approach to credit scoring is to pursue a “winner-take-all” perspective by which, for each dataset, a single believed to be the “best” statistical learning or machine learning classifier is selected from a set of candidate approaches using some method or criteria often neglecting model uncertainty. This paper empirically investigates the predictive accuracy of single-based classifiers against the stacking generalization approach in credit risk modelling using real-world peer-to-peer lending data. The findings show that stacking ensembles consistently outperform most traditional individual credit scoring models in predicting the default probability. Moreover, the findings show that adopting a feature selection process and hyperparameter tuning contributes to improving the performance of individual credit risk models and the super-learner scoring algorithm, helping models to be simpler, more comprehensive, and with lower classification error rates. Improving credit scoring models to better identify loan delinquency can substantially contribute to reducing loan impairments and losses leading to an improvement in the financial performance of credit institutions.
Original languageEnglish
Title of host publicationInformation Systems and Technologies
Subtitle of host publicationWorldCIST 2023, Volume 1
EditorsÁlvaro Rocha, Hojjat Adeli, Gintautas Dzemyda, Fernando Moreira, Valentina Colla
Place of PublicationGewerbestrasse, Cham
PublisherSpringer
Pages382-396
Number of pages15
Volume1
ISBN (Electronic)978-3-031-45642-8
ISBN (Print)978-3-031-45641-1
DOIs
Publication statusPublished - 16 Feb 2024
Event11th World Conference on Information Systems and Technologies 2023 - Hotel Galilei, Pisa, Italy
Duration: 4 Apr 20236 Apr 2023
Conference number: 11
http://www.worldcist.org/2023/

Publication series

NameLecture Notes in Networks and Systems
PublisherSpringer Cham
Volume799
ISSN (Print)2367-3370
ISSN (Electronic)2367-3389

Conference

Conference11th World Conference on Information Systems and Technologies 2023
Abbreviated titleWorldCist'23
Country/TerritoryItaly
CityPisa
Period4/04/236/04/23
Internet address

Keywords

  • Credit scoring
  • Ensemble learning
  • Probability of default
  • Stacking generalization
  • Risk management

Fingerprint

Dive into the research topics of 'Credit Risk Scoring: A Stacking Generalization Approach'. Together they form a unique fingerprint.

Cite this