Improving Explanations: Applying the Feature Understandability Scale for Cost-Sensitive Feature Selection

TL;DR

This paper introduces a co-optimization approach for balancing model accuracy and feature understandability in explanations, demonstrating that both can be improved simultaneously for better interpretability.

Contribution

It extends the Feature Understandability Scale to optimize explanations alongside accuracy, providing a novel method for more interpretable AI models.

Findings

Accuracy and understandability can be co-optimized successfully.

The explanations produced are more understandable without sacrificing performance.

Further user studies are planned to validate these findings.

Abstract

With the growing pervasiveness of artificial intelligence, the ability to explain the inferences made by machine learning models has become increasingly important. Numerous techniques for model explainability have been proposed, with natural-language textual explanations among the most widely used approaches. When applied to tabular data, these explanations typically draw on input features to justify a given inference. Consequently, a user's ability to interpret the explanation depends on their understanding of the input features. To quantify this feature-level understanding, Rossberg et al. introduced the Feature Understandability Scale. Building on that work, this proof-of-concept study collects understandability scores across two datasets, proposes a co-optimisation methodology of understandability and accuracy and presents the resulting explanations alongside the model accuracies. This work contributes to the body of knowledge on model interpretability by design. It is found that accuracy and understandability can be successfully co-optimised while maintaining high classification performances. The resulting explanations are considered more understandable at face value. Further research will aim to confirm these findings through user evaluation.