Hybrid Decision Making: When Interpretable Models Collaborate With Black-Box Models

Interpretable machine learning models have received increasing interest in recent years, especially in domains where humans are involved in the decision-making process. However, the possible loss of the task performance for gaining interpretability is o‰en inevitable. Œis performance downgrade puts practitioners in a dilemma of choosing between a top-performing black-box model with no explanations and an interpretable model with unsatisfying task performance. In this work, we propose a novel framework for building a Hybrid Decision Model that integrates an interpretable model with any black-box model to introduce explanations in the decision making process while preserving or possibly improving the predictive accuracy. We propose a novel metric, explainability, to measure the percentage of data that are sent to the interpretable model for decision. We also design a principled objective function that considers predictive accuracy, model interpretability, and data explainability. Under this framework, we develop Collaborative Black-box and RUle Set Hybrid (CoBRUSH) model that combines logic rules and any black-box model into a joint decision model. An input instance is €rst sent to the rules for decision. If a rule is satis€ed, a decision will be directly generated. Otherwise, the black-box model is activated to decide on the instance. To train a hybrid model, we design an ecient search algorithm that exploits theoretically grounded strategies to reduce computation. Experiments show that CoBRUSH models are able to achieve same or beŠer accuracy than their black-box collaborator working alone while gaining explainability. Œey also have smaller model complexity than interpretable baselines.