Conformalized Exceptional Model Mining: Telling Where Your Model Performs (Not) Well
This addresses the need for responsible model deployment in high-stakes domains like healthcare and finance by enhancing interpretability and reliability, though it is incremental as it builds on existing methods.
The paper tackles the problem of understanding nuanced model performance by introducing Conformalized Exceptional Model Mining, which identifies cohesive subgroups in data where performance deviates exceptionally, using a new model class and quality measure to provide interpretable insights.
Understanding the nuanced performance of machine learning models is essential for responsible deployment, especially in high-stakes domains like healthcare and finance. This paper introduces a novel framework, Conformalized Exceptional Model Mining, which combines the rigor of Conformal Prediction with the explanatory power of Exceptional Model Mining (EMM). The proposed framework identifies cohesive subgroups within data where model performance deviates exceptionally, highlighting regions of both high confidence and high uncertainty. We develop a new model class, mSMoPE (multiplex Soft Model Performance Evaluation), which quantifies uncertainty through conformal prediction's rigorous coverage guarantees. By defining a new quality measure, Relative Average Uncertainty Loss (RAUL), our framework isolates subgroups with exceptional performance patterns in multi-class classification and regression tasks. Experimental results across diverse datasets demonstrate the framework's effectiveness in uncovering interpretable subgroups that provide critical insights into model behavior. This work lays the groundwork for enhancing model interpretability and reliability, advancing the state-of-the-art in explainable AI and uncertainty quantification.