Please use this identifier to cite or link to this item:
Title: Towards Global Explanations for Credit Risk Scoring
Author: Unceta, Irene
Nin, Jordi
Pujol Vila, Oriol
Keywords: Risc de crèdit
Credit risk
Issue Date: 23-Nov-2018
Publisher: Neural Information Processing Systems Foundation
Abstract: In this paper we propose a method to obtain global explanations for trained black-box classifiers by sampling their decision function to learn alternative interpretable models. The envisaged approach provides a unified solution to approximate non-linear decision boundaries with simpler classifiers while retaining the original classification accuracy. We use a private residential mortgage default dataset as a use case to illustrate the feasibility of this approach to ensure the decomposability of attributes during pre-processing.
It is part of: Comunicació a: NIPS 2018 Workshop on Challenges and Opportunities for AI in Financial Services: the Impact of Fairness, Explainability, Accuracy, and Privacy, Montréal, Canada. December 7th, 2018
Appears in Collections:Comunicacions a congressos (Matemàtiques i Informàtica)

Files in This Item:
File Description SizeFormat 
UncetaNIPS18.pdf1.72 MBAdobe PDFView/Open

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.