Quantifying Visual Properties of GAM Shape Plots: Impact on Perceived Cognitive Load and Interpretability
This addresses the issue of interpretability in machine learning for users by providing a tool to predict cognitive load without direct involvement, though it is incremental as it builds on existing GAM methods.
The study tackled the problem of how visual properties of GAM shape plots affect cognitive load and interpretability, finding that the number of kinks explains 86.4% of the variance in user ratings.
Generalized Additive Models (GAMs) offer a balance between performance and interpretability in machine learning. The interpretability aspect of GAMs is expressed through shape plots, representing the model's decision-making process. However, the visual properties of these plots, e.g. number of kinks (number of local maxima and minima), can impact their complexity and the cognitive load imposed on the viewer, compromising interpretability. Our study, including 57 participants, investigates the relationship between the visual properties of GAM shape plots and cognitive load they induce. We quantify various visual properties of shape plots and evaluate their alignment with participants' perceived cognitive load, based on 144 plots. Our results indicate that the number of kinks metric is the most effective, explaining 86.4% of the variance in users' ratings. We develop a simple model based on number of kinks that provides a practical tool for predicting cognitive load, enabling the assessment of one aspect of GAM interpretability without direct user involvement.