Journal
JOURNAL OF MACHINE LEARNING RESEARCH
Volume 24, Issue -, Pages -Publisher
MICROTOME PUBL
Keywords
Explainable Artificial Intelligence (XAI); Local Explanations; Interpretability; Credit Risk
Ask authors/readers for more resources
This research presents a method for understanding specific predictions made by global predictive models. It focuses on constructing local models tailored to each specific observation and using rule-based models. Multiple algorithms are designed to extract rules from different datasets, and the method is applied to credit-risk models successfully.
We develop a method for understanding 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 the Explainable Machine Learning Challenge data from FICO and demonstrate that our approach effectively produces sparse summary-explanations of these models in seconds. Our approach is model-agnostic (that is, can be used to explain any predictive model), and solves a minimum set cover problem to construct its summaries.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available