RT Journal Article
T1 A new approach based on association rules to add explainability to time series forecasting models
A1 Troncoso-García, Ángela R.
A1 Martínez Ballesteros, María
A1 Martínez-Álvarez, Francisco
A1 Troncoso, Alicia
K1 Explainable AI
K1 Machine learning
K1 Time series forecasting
K1 Interpretability
K1 Association rules
AB Machine learning and deep learning have become the most useful and powerful tools in the last years to mine information from large datasets. Despite the successful application to many research fields, it is widely known that some of these solutions based on artificial intelligence are considered black-box models, meaning that most experts find difficult to explain and interpret the models and why they generate such outputs. In this context, explainable artificial intelligence is emerging with the aim of providing black-box models with sufficient interpretability. Thus, models could be easily understood and further applied. This work proposes a novel method to explain black-box models, by using numeric association rules to explain and interpret multi-step time series forecasting models. Thus, a multi-objective algorithm is used to discover quantitative association rules from the target model. Then, visual explanation techniques are applied to make the rules more interpretable. Data from Spanish electricity energy consumption has been used to assess the suitability of the proposal.
PB Elsevier
YR 2023
FD 2023-01-26
LK https://hdl.handle.net/10433/25817
UL https://hdl.handle.net/10433/25817
LA en
NO A.R. Troncoso-García, M. Martínez-Ballesteros, F. Martínez-Álvarez, A. Troncoso, A new approach based on association rules to add explainability to time series forecasting models, Information Fusion, Volume 94, 2023, Pages 169-180, ISSN 1566-2535, https://doi.org/10.1016/j.inffus.2023.01.021
NO UPO
DS RIO
RD May 9, 2026