ConceptCF: Concept-based Counterfactuals for the Explainability of Time Series

2026-07-21

AI Summary

This work addresses the limited semantic interpretability of existing counterfactual explanation methods for time series, which often rely on spurious correlations rather than genuine causal mechanisms. To overcome this, the study introduces human-understandable time series concepts—such as scale and frequency band—into counterfactual generation for the first time. By decomposing time series into a concept space grounded in domain knowledge, the method employs a genetic algorithm to search for minimal perturbations within this space that alter model predictions. The resulting explanations are not only semantically clear and aligned with expert understanding but also consistently outperform five state-of-the-art baselines across multiple evaluation criteria, including validity, confidence, proximity, sparsity, and plausibility, thereby achieving the current best performance in time series counterfactual explanation.

Abstract

This paper proposes ConceptCF, a method for counterfactual generation that operates on human-interpretable concepts. In high-stakes domains such as healthcare and predictive maintenance, artificial intelligence models can increase efficiency and safety. Explainability is key to ensure these models rely on causal relationships rather than spurious correlations. Counterfactual explanations identify minimal modifications that would change a model's predictions. Existing methods for time series operate on individual points or subsequences without ensuring interpretability of the mutations. ConceptCF instead modifies meaningful concepts. As a result we can provide explanations in terms of these concepts, for example ``the model's prediction would be `Sit' instead of `Walk' if you increase the scale of the movement''. In this paper, the concepts are constructed through time series decomposition, resulting in concepts such as scale, and frequency bands. Counterfactuals are generated using a genetic algorithm that optimizes the concept mutations. Evaluation against five state-of-the-art approaches demonstrates that ConceptCF consistently achieves top-tier performance across validity, confidence, proximity, sparsity and plausibility metrics.

Problem

• counterfactual explanations
• time series
• explainability
• interpretable concepts
• spurious correlations

Innovation

• concept-based counterfactuals
• time series explainability
• interpretable concepts
• genetic algorithm
• time series decomposition