Back to Search
Start Over
Testing machine learning explanation methods.
- Source :
-
Neural Computing & Applications . Aug2023, Vol. 35 Issue 24, p18073-18084. 12p. - Publication Year :
- 2023
-
Abstract
- There are many methods for explaining why a machine learning model produces a given output in response to a given input. The relative merits of these methods are often debated using theoretical arguments and illustrative examples. This paper provides a large-scale empirical test of four widely used explanation methods by comparing how well their algorithmically generated denial reasons align with lender-provided denial reasons using a dataset of home mortgage applications. On a held-out sample of 10,000 denied applications, Shapley additive explanations (SHAP) correspond most closely with lender-provided reasons. SHAP is also the most computationally efficient. As a second contribution, this paper presents a method for computing integrated gradient explanations that can be used for non-differentiable models such as XGBoost. [ABSTRACT FROM AUTHOR]
- Subjects :
- *MACHINE learning
*EXPLANATION
Subjects
Details
- Language :
- English
- ISSN :
- 09410643
- Volume :
- 35
- Issue :
- 24
- Database :
- Academic Search Index
- Journal :
- Neural Computing & Applications
- Publication Type :
- Academic Journal
- Accession number :
- 167308529
- Full Text :
- https://doi.org/10.1007/s00521-023-08597-8