Local and Global Explainability Metrics for Machine Learning Predictions

by   Cristian Muñoz, et al.

Rapid advancements in artificial intelligence (AI) technology have brought about a plethora of new challenges in terms of governance and regulation. AI systems are being integrated into various industries and sectors, creating a demand from decision-makers to possess a comprehensive and nuanced understanding of the capabilities and limitations of these systems. One critical aspect of this demand is the ability to explain the results of machine learning models, which is crucial to promoting transparency and trust in AI systems, as well as fundamental in helping machine learning models to be trained ethically. In this paper, we present novel quantitative metrics frameworks for interpreting the predictions of classifier and regressor models. The proposed metrics are model agnostic and are defined in order to be able to quantify: i. the interpretability factors based on global and local feature importance distributions; ii. the variability of feature impact on the model output; and iii. the complexity of feature interactions within model decisions. We employ publicly available datasets to apply our proposed metrics to various machine learning models focused on predicting customers' credit risk (classification task) and real estate price valuation (regression task). The results expose how these metrics can provide a more comprehensive understanding of model predictions and facilitate better communication between decision-makers and stakeholders, thereby increasing the overall transparency and accountability of AI systems.


page 1

page 2

page 3

page 4


Explainable AI in Credit Risk Management

Artificial Intelligence (AI) has created the single biggest technology r...

A Brief Review of Explainable Artificial Intelligence in Healthcare

XAI refers to the techniques and methods for building AI applications wh...

ComplAI: Theory of A Unified Framework for Multi-factor Assessment of Black-Box Supervised Machine Learning Models

The advances in Artificial Intelligence are creating new opportunities t...

Metric Tools for Sensitivity Analysis with Applications to Neural Networks

As Machine Learning models are considered for autonomous decisions with ...

Comparative evaluation of contribution-value plots for machine learning understanding

The field of explainable artificial intelligence aims to help experts un...

Interpreting Machine Learning Models for Room Temperature Prediction in Non-domestic Buildings

An ensuing challenge in Artificial Intelligence (AI) is the perceived di...

A Framework for Auditing Multilevel Models using Explainability Methods

Applications of multilevel models usually result in binary classificatio...

Please sign up or login with your details

Forgot password? Click here to reset