RuleXAI—A package for rule-based explanations of machine learning model
The ability to use eXplainable Artificial Intelligence (XAI) methods is very important for both AI users and AI developers. This paper presents the RuleXAI library, which provides XAI methods based on rule-based models. The package presented can be applied to classification, regression and survival...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2022-12-01
|
Series: | SoftwareX |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S2352711022001273 |
_version_ | 1811187291991834624 |
---|---|
author | Dawid Macha Michał Kozielski Łukasz Wróbel Marek Sikora |
author_facet | Dawid Macha Michał Kozielski Łukasz Wróbel Marek Sikora |
author_sort | Dawid Macha |
collection | DOAJ |
description | The ability to use eXplainable Artificial Intelligence (XAI) methods is very important for both AI users and AI developers. This paper presents the RuleXAI library, which provides XAI methods based on rule-based models. The package presented can be applied to classification, regression and survival analysis tasks. RuleXAI operates on elementary rule conditions and enables the generation of global explanations, local explanations and the generation of a new data representation, simplifying data preprocessing. The explanations of model decisions that are generated by RuleXAI rely on feature relevance and provide information not only about the importance of attributes, but also about the importance of attribute values. |
first_indexed | 2024-04-11T14:00:55Z |
format | Article |
id | doaj.art-ef12732d0b834d7795c47c5bac69d5a1 |
institution | Directory Open Access Journal |
issn | 2352-7110 |
language | English |
last_indexed | 2024-04-11T14:00:55Z |
publishDate | 2022-12-01 |
publisher | Elsevier |
record_format | Article |
series | SoftwareX |
spelling | doaj.art-ef12732d0b834d7795c47c5bac69d5a12022-12-22T04:20:08ZengElsevierSoftwareX2352-71102022-12-0120101209RuleXAI—A package for rule-based explanations of machine learning modelDawid Macha0Michał Kozielski1Łukasz Wróbel2Marek Sikora3Łukasiewicz Research Network – Institute of Innovative Technologies EMAG, ul. Leopolda 31, Katowice 40-189, PolandDepartment of Computer Networks and Systems, Silesian University of Technology, ul. Akademicka 16, 44-100 Gliwice, PolandDepartment of Computer Networks and Systems, Silesian University of Technology, ul. Akademicka 16, 44-100 Gliwice, PolandDepartment of Computer Networks and Systems, Silesian University of Technology, ul. Akademicka 16, 44-100 Gliwice, Poland; Corresponding author.The ability to use eXplainable Artificial Intelligence (XAI) methods is very important for both AI users and AI developers. This paper presents the RuleXAI library, which provides XAI methods based on rule-based models. The package presented can be applied to classification, regression and survival analysis tasks. RuleXAI operates on elementary rule conditions and enables the generation of global explanations, local explanations and the generation of a new data representation, simplifying data preprocessing. The explanations of model decisions that are generated by RuleXAI rely on feature relevance and provide information not only about the importance of attributes, but also about the importance of attribute values.http://www.sciencedirect.com/science/article/pii/S2352711022001273XAIRule-based representationGlobal explanationsLocal explanationsFeature relevancePython |
spellingShingle | Dawid Macha Michał Kozielski Łukasz Wróbel Marek Sikora RuleXAI—A package for rule-based explanations of machine learning model SoftwareX XAI Rule-based representation Global explanations Local explanations Feature relevance Python |
title | RuleXAI—A package for rule-based explanations of machine learning model |
title_full | RuleXAI—A package for rule-based explanations of machine learning model |
title_fullStr | RuleXAI—A package for rule-based explanations of machine learning model |
title_full_unstemmed | RuleXAI—A package for rule-based explanations of machine learning model |
title_short | RuleXAI—A package for rule-based explanations of machine learning model |
title_sort | rulexai a package for rule based explanations of machine learning model |
topic | XAI Rule-based representation Global explanations Local explanations Feature relevance Python |
url | http://www.sciencedirect.com/science/article/pii/S2352711022001273 |
work_keys_str_mv | AT dawidmacha rulexaiapackageforrulebasedexplanationsofmachinelearningmodel AT michałkozielski rulexaiapackageforrulebasedexplanationsofmachinelearningmodel AT łukaszwrobel rulexaiapackageforrulebasedexplanationsofmachinelearningmodel AT mareksikora rulexaiapackageforrulebasedexplanationsofmachinelearningmodel |