Globally-Consistent Rule-Based Summary-Explanations for Machine Learning Models: Application to Credit-Risk Evaluation

19 Pages Posted: 12 Jun 2019

See all articles by Cynthia Rudin

Cynthia Rudin

Duke University - Pratt School of Engineering; Duke University

Yaron Shaposhnik

University of Rochester - Simon Business School

Date Written: May 28, 2019

Abstract

We develop a method for interpreting specific predictions made by (global) predictive models by constructing (local) models tailored to each specific observation (these are also called "explanations" in the literature). Unlike existing work that "explains'' specific observations by approximating global models in the vicinity of these observations, we fit models that are globally consistent with predictions made by the global model on past data. We focus on rule-based models (also known as association rules or conjunctions of predicates), which are interpretable and widely used in practice. We design multiple algorithms to extract such rules from discrete and continuous datasets, and study their theoretical properties. Finally, we apply these algorithms to multiple credit-risk models trained on real-world data from FICO and demonstrate that our approach effectively produces sparse summary-explanations of these models in short period of time. Our approach is model-agnostic (that is, can be used to interpret any predictive model), and solves a minimum set cover problem to construct its summaries.

Keywords: Interpretability, Local models, Association rules, Explanations, Machine learning, Credit-risk

JEL Classification: C4, C19

Suggested Citation

Rudin, Cynthia and Shaposhnik, Yaron, Globally-Consistent Rule-Based Summary-Explanations for Machine Learning Models: Application to Credit-Risk Evaluation (May 28, 2019). Available at SSRN: https://ssrn.com/abstract=3395422 or http://dx.doi.org/10.2139/ssrn.3395422

Cynthia Rudin

Duke University - Pratt School of Engineering ( email )

Durham, NC 27708
United States

Duke University ( email )

Department of Computer Science
LSRC Building
Durham, NC 27708-0204
United States

Yaron Shaposhnik (Contact Author)

University of Rochester - Simon Business School ( email )

Rochester, NY 14627
United States

Register to save articles to
your library

Register

Paper statistics

Downloads
104
Abstract Views
332
rank
259,745
PlumX Metrics