Using Hybrid Approaches for Credit Application Scoring
No Thumbnail Available
Date
2023
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Institute of Electrical and Electronics Engineers Inc.
Open Access Color
OpenAIRE Downloads
OpenAIRE Views
Abstract
Using various methods of computational intelligence, scores for credit applications are predicted for making a decision to accept or to reject. Past data about credits accepted in a financial institution are used to develop hybrid models implementing gradient boosting and attention supported neural networks. The performance (Gini scores above 0.7), limitations and further research directions are discussed. © 2023 IEEE.
Description
Keywords
attention mechanism, credit scoring, gradient boosting, neural networks, unbalanced data
Turkish CoHE Thesis Center URL
Fields of Science
Citation
0
WoS Q
N/A
Scopus Q
N/A
Source
IEEE 23rd International Symposium on Computational Intelligence and Informatics, CINTI 2023 - Proceedings -- 23rd IEEE International Symposium on Computational Intelligence and Informatics, CINTI 2023 -- 20 November 2023 through 22 November 2023 -- Budapest -- 196335
Volume
Issue
Start Page
111
End Page
116