An Interpretable Model with Globally Consistent Explanations for Credit Risk

Abstract

We propose a possible solution to a public challenge posed by the Fair Isaac Corporation (FICO), which is to provide an explainable model for credit risk assessment. Rather than present a black box model and explain it afterwards, we provide a globally interpretable model that is as accurate as other neural networks. Our "two-layer additive risk model" is decomposable into subscales, where each node in the second layer represents a meaningful subscale, and all of the nonlinearities are transparent. We provide three types of explanations that are simpler than, but consistent with, the global model. One of these explanation methods involves solving a minimum set cover problem to find high-support globally-consistent explanations. We present a new online visualization tool to allow users to explore the global model and its explanations.

Keywords

Cover (algebra)Set (abstract data type)Computer scienceArtificial neural networkNode (physics)Black boxCredit riskLayer (electronics)Risk modelEconometricsArtificial intelligenceActuarial scienceMathematicsEconomicsEngineering

Related Publications

Grad-CAM++: Generalized Gradient-Based Visual Explanations for Deep Convolutional Networks

Aditya Chattopadhay , Anirban Sarkar , Prantik Howlader +1 more

Over the last decade, Convolutional Neural Network (CNN) models have been\nhighly successful in solving complex vision problems. However, these deep\nmodels are perceived as "bl...

2018 2018 IEEE Winter Conference on Applic... 2688 citations

On a Method to Measure Supervised Multiclass Model’s Interpretability: Application to Degradation Diagnosis (Short Paper)

Scott Lundberg , Su‐In Lee

In an industrial maintenance context, degradation diagnosis is the problem of determining the current level of degradation of operating machines based on measurements. With the ...

2024 Dagstuhl Research Online Publication ... 12892 citations

Anchors: High-Precision Model-Agnostic Explanations

Marco Túlio Ribeiro , Sameer Singh , Carlos Guestrin

We introduce a novel model-agnostic system that explains the behavior of complex models with high-precision rules called anchors, representing local, "sufficient" conditions for...

2018 Proceedings of the AAAI Conference on... 1932 citations

Model Agnostic Supervised Local Explanations

Gregory Plumb , Denali Molitor , Ameet Talwalkar

Model interpretability is an increasingly important component of practical machine learning. Some of the most common forms of interpretability systems are example-based, local, ...

2018 arXiv (Cornell University) 113 citations

Deep Learning for Case-Based Reasoning Through Prototypes: A Neural Network That Explains Its Predictions

Oscar Li , Hao Liu , Chaofan Chen +1 more

Deep neural networks are widely used for classification. These deep models often suffer from a lack of interpretability---they are particularly difficult to understand because o...

2018 Proceedings of the AAAI Conference on... 390 citations

Publication Info

Year: 2018
Type: preprint
Citations: 65
Access: Closed

External Links

View on DOI.org

Social Impact

Altmetric

An Interpretable Model with Globally Consistent Explanations for Credit Risk

PlumX Metrics

Social media, news, blog, policy document mentions

Citation Metrics

OpenAlex

Cite This

APA Style

                            
                                    Chaofan Chen, 
                                
                                    Kangcheng Lin, 
                                
                                    Cynthia Rudin
                                
                                et al.
                            
                            (2018). 
                            An Interpretable Model with Globally Consistent Explanations for Credit Risk. 
                            arXiv (Cornell University)
                            
                            .
                            https://doi.org/10.48550/arxiv.1811.12615

Identifiers

DOI: 10.48550/arxiv.1811.12615