RT Journal Article
T1 A new metric based on association rules to assess feature-attribution explainability techniques for time series forecasting
A1 Troncoso-García, Ángela R.
A1 Martínez-Ballesteros, María
A1 Martínez-Álvarez, Francisco
A1 Troncoso, Alicia
K1 Explainable artificial intelligence
K1 Attributionbased explainability
K1 Association rules
K1 Time series forecasting
AB This paper introduces a new, model-independent, metric, called RExQUAL, for quantifying the quality of explanations provided by attribution-based explainable artificial intelligence techniques and compare them. The underlying idea is based on feature attribution, using a subset of the ranking of the attributes highlighted by a model-agnostic explainable method in a forecasting task. Then, association rules are generated using these key attributes as input data. Novel metrics, including global support and confidence, are proposed to assess the joint quality of generated rules. Finally, the quality of the explanations is calculated based on a wise and comprehensive combination of the association rules global metrics. The proposed method integrates local explanations through attribution-based approaches for evaluation and feature selection with global explanations for the entire dataset. This paper rigorously evaluates the new metric by comparing three explainability techniques: the widely used SHAP and LIME, and the novel methodology RULEx. The experimental design includes predicting time series of different natures, including univariate and multivariate, through deep learning models. The results underscore the efficacy and versatility of the proposed methodology as a quantitative framework for evaluating and comparing explainable techniques.
PB IEEE
YR 2025
FD 2025-05-20
LK https://hdl.handle.net/10433/25738
UL https://hdl.handle.net/10433/25738
LA en
NO Á. R. Troncoso-García, M. Martínez-Ballesteros, F. Martínez-Álvarez and A. Troncoso, "A New Metric Based on Association Rules to Assess Feature-Attribution Explainability Techniques for Time Series Forecasting," in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 47, no. 5, pp. 4140-4155, May 2025, doi: 10.1109/TPAMI.2025.3540513
NO UPO
DS RIO
RD May 9, 2026