WISCA: A Consensus-Based Approach to Harmonizing Interpretability in Tabular Datasets
For practitioners in high-stakes domains needing reliable model explanations, WISCA provides a robust consensus strategy to improve interpretability reliability.
WISCA harmonizes conflicting explanations from different interpretability algorithms by integrating class probability and normalized attributions, consistently aligning with the most reliable individual method across six synthetic datasets.
While predictive accuracy is often prioritized in machine learning (ML) models, interpretability remains essential in scientific and high-stakes domains. However, diverse interpretability algorithms frequently yield conflicting explanations, highlighting the need for consensus to harmonize results. In this study, six ML models were trained on six synthetic datasets with known ground truths, utilizing various model-agnostic interpretability techniques. Consensus explanations were generated using established methods and a novel approach: WISCA (Weighted Scaled Consensus Attributions), which integrates class probability and normalized attributions. WISCA consistently aligned with the most reliable individual method, underscoring the value of robust consensus strategies in improving explanation reliability.