Journal article
A holistic approach to interpretability in financial lending: Models, visualizations, and summary-explanations
Decision Support Systems, Vol.152, p.113647
01/01/2022
DOI: 10.1016/j.dss.2021.113647
Abstract
•Introduction of a DSS for financial lending that includes several AI approaches that form a holistic approach. A novel globally interpretable two-layer additive risk model, which lends naturally to sparsity, decomposability, visualization, case-based reasoning, feature importance, and monotonicity constraints.•An interactive visualization tool for the model and its local explanations.•An application of our approach to finance, indicating that black-box models may not be necessary in the case of credit-risk assessment.
Lending decisions are usually made with proprietary models that provide minimally acceptable explanations to users. In a future world without such secrecy, what decision support tools would one want to use for justified lending decisions? This question is timely, since the economy has dramatically shifted due to a pandemic, and a massive number of new loans will be necessary in the short term. We propose a framework for such decisions, including a globally interpretable machine learning model, an interactive visualization of it, and several types of summaries and explanations for any given decision. The machine learning model is a two-layer additive risk model, which resembles a two-layer neural network, but is decomposable into subscales. In this model, each node in the first (hidden) layer represents a meaningful subscale model, and all of the nonlinearities are transparent. Our online visualization tool allows exploration of this model, showing precisely how it came to its conclusion. We provide three types of explanations that are simpler than, but consistent with, the global model: case-based reasoning explanations that use neighboring past cases, a set of features that were the most important for the model's prediction, and summary-explanations that provide a customized sparse explanation for any particular lending decision made by the model. Our framework earned the FICO recognition award for the Explainable Machine Learning Challenge, which was the first public challenge in the domain of explainable machine learning.11Authors are listed alphabetically.
Details
- Title: Subtitle
- A holistic approach to interpretability in financial lending: Models, visualizations, and summary-explanations
- Creators
- Chaofan Chen - University of MaineKangcheng Lin - University of Illinois Urbana-ChampaignCynthia Rudin - Duke UniversityYaron Shaposhnik - University of RochesterSijia Wang - Duke UniversityTong Wang - University of Iowa
- Resource Type
- Journal article
- Publication Details
- Decision Support Systems, Vol.152, p.113647
- Publisher
- Elsevier B.V
- DOI
- 10.1016/j.dss.2021.113647
- ISSN
- 0167-9236
- eISSN
- 1873-5797
- Language
- English
- Date published
- 01/01/2022
- Academic Unit
- Business Analytics
- Record Identifier
- 9984380491802771
Metrics
2 Record Views