Evaluating the Quality of Counterfactual Explanations in Multivariate Time-Series

Counterfactual explanations (CFEs) offer a promising approach for understanding personalized psychological processes captured through Ecological Momentary Assessment (EMA). In particular, generating CFEs for time points associated with mental health deterioration can help identify alternative changes that might prevent such outcomes. To assess the quality of generated CFEs on time-series data, we propose a 3-level framework: per explanation (based on feature changes, proximity, and model confidence), per time point (based on structure and diversity through clustering), and per individual temporal dynamics. Applying this framework to a real-world time-series EMA dataset, we demonstrate how we assess the validity and interpretability of large volumes of CFEs.