Assessing Robustness of Machine Learning Models using Covariate Perturbations

TL;DR

This paper introduces a comprehensive framework for evaluating the robustness of machine learning models against covariate perturbations, addressing stability issues in critical applications like healthcare and finance.

Contribution

It proposes novel perturbation strategies and diagnostic tools to assess and improve model robustness across different data scenarios.

Findings

Effective in identifying model instabilities

Enables comparison of robustness across models

Improves model stability through targeted analysis

Abstract

As machine learning models become increasingly prevalent in critical decision-making models and systems in fields like finance, healthcare, etc., ensuring their robustness against adversarial attacks and changes in the input data is paramount, especially in cases where models potentially overfit. This paper proposes a comprehensive framework for assessing the robustness of machine learning models through covariate perturbation techniques. We explore various perturbation strategies to assess robustness and examine their impact on model predictions, including separate strategies for numeric and non-numeric variables, summaries of perturbations to assess and compare model robustness across different scenarios, and local robustness diagnosis to identify any regions in the data where a model is particularly unstable. Through empirical studies on real world dataset, we demonstrate the effectiveness of our approach in comparing robustness across models, identifying the instabilities in the model, and enhancing model robustness.