A new approach based on association rules to add explainability to time series forecasting models

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 bla...

Descripción completa

Detalles Bibliográficos
Autores: Troncoso García, Ángela del Robledo, Martínez Ballesteros, María del Mar, Martínez Álvarez, Francisco, Troncoso Lora, Alicia
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2023
País:España
Institución:Universidad de Sevilla (US)
Repositorio:idUS. Depósito de Investigación de la Universidad de Sevilla
OAI Identifier:oai:idus.us.es:11441/146052
Acceso en línea:https://hdl.handle.net/11441/146052
https://doi.org/10.1016/j.inffus.2023.01.021
Access Level:acceso abierto
Palabra clave:Explainable AI
Machine learning
Time series forecasting
Interpretability
Association rules
id ES_58d876be5f1675754cda0a96f528f708
oai_identifier_str oai:idus.us.es:11441/146052
network_acronym_str ES
network_name_str España
repository_id_str
spelling A new approach based on association rules to add explainability to time series forecasting modelsTroncoso García, Ángela del RobledoMartínez Ballesteros, María del MarMartínez Álvarez, FranciscoTroncoso Lora, AliciaExplainable AIMachine learningTime series forecastingInterpretabilityAssociation rulesMachine 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.Ministerio de Ciencia e Innovación PID2020-117954RB-C21Ministerio de Ciencia e Innovación TED2021-131311B-C22Junta de Andalucía PY20-00870Junta de Andalucía UPO-138516ScienceDirectLenguajes y Sistemas InformáticosMinisterio de Ciencia e Innovación (MICIN). EspañaJunta de Andalucía2023info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfapplication/pdfhttps://hdl.handle.net/11441/146052https://doi.org/10.1016/j.inffus.2023.01.021reponame:idUS. Depósito de Investigación de la Universidad de Sevillainstname:Universidad de Sevilla (US)InglésInformation Fusion, 94, 169-180.PID2020-117954RB-C21TED2021-131311B-C22PY20-00870UPO-138516https://www.sciencedirect.com/science/article/pii/S1566253523000295?via%3Dihubinfo:eu-repo/semantics/openAccessoai:idus.us.es:11441/1460522026-06-17T12:51:07Z
dc.title.none.fl_str_mv A new approach based on association rules to add explainability to time series forecasting models
title A new approach based on association rules to add explainability to time series forecasting models
spellingShingle A new approach based on association rules to add explainability to time series forecasting models
Troncoso García, Ángela del Robledo
Explainable AI
Machine learning
Time series forecasting
Interpretability
Association rules
title_short A new approach based on association rules to add explainability to time series forecasting models
title_full A new approach based on association rules to add explainability to time series forecasting models
title_fullStr A new approach based on association rules to add explainability to time series forecasting models
title_full_unstemmed A new approach based on association rules to add explainability to time series forecasting models
title_sort A new approach based on association rules to add explainability to time series forecasting models
dc.creator.none.fl_str_mv Troncoso García, Ángela del Robledo
Martínez Ballesteros, María del Mar
Martínez Álvarez, Francisco
Troncoso Lora, Alicia
author Troncoso García, Ángela del Robledo
author_facet Troncoso García, Ángela del Robledo
Martínez Ballesteros, María del Mar
Martínez Álvarez, Francisco
Troncoso Lora, Alicia
author_role author
author2 Martínez Ballesteros, María del Mar
Martínez Álvarez, Francisco
Troncoso Lora, Alicia
author2_role author
author
author
dc.contributor.none.fl_str_mv Lenguajes y Sistemas Informáticos
Ministerio de Ciencia e Innovación (MICIN). España
Junta de Andalucía
dc.subject.none.fl_str_mv Explainable AI
Machine learning
Time series forecasting
Interpretability
Association rules
topic Explainable AI
Machine learning
Time series forecasting
Interpretability
Association rules
description 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.
publishDate 2023
dc.date.none.fl_str_mv 2023
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv https://hdl.handle.net/11441/146052
https://doi.org/10.1016/j.inffus.2023.01.021
url https://hdl.handle.net/11441/146052
https://doi.org/10.1016/j.inffus.2023.01.021
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv Information Fusion, 94, 169-180.
PID2020-117954RB-C21
TED2021-131311B-C22
PY20-00870
UPO-138516
https://www.sciencedirect.com/science/article/pii/S1566253523000295?via%3Dihub
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.publisher.none.fl_str_mv ScienceDirect
publisher.none.fl_str_mv ScienceDirect
dc.source.none.fl_str_mv reponame:idUS. Depósito de Investigación de la Universidad de Sevilla
instname:Universidad de Sevilla (US)
instname_str Universidad de Sevilla (US)
reponame_str idUS. Depósito de Investigación de la Universidad de Sevilla
collection idUS. Depósito de Investigación de la Universidad de Sevilla
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869408571948531712
score 15,300719

Similares en LA Referencia