{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,15]],"date-time":"2026-02-15T03:19:24Z","timestamp":1771125564442,"version":"3.50.1"},"reference-count":21,"publisher":"MIT Press","issue":"4","license":[{"start":{"date-parts":[[2023,8,23]],"date-time":"2023-08-23T00:00:00Z","timestamp":1692748800000},"content-version":"vor","delay-in-days":234,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["direct.mit.edu"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,11,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>In sociotechnical settings, human operators are increasingly assisted by decision support systems. By employing such systems, important properties of sociotechnical systems, such as self-adaptation and self-optimization, are expected to improve further. To be accepted by and engage efficiently with operators, decision support systems need to be able to provide explanations regarding the reasoning behind specific decisions. In this article, we propose the use of learning classifier systems (LCSs), a family of rule-based machine learning methods, to facilitate and highlight techniques to improve transparent decision-making. Furthermore, we present a novel approach to assessing application-specific explainability needs for the design of LCS models. For this, we propose an application-independent template of seven questions. We demonstrate the approach\u2019s use in an interview-based case study for a manufacturing scenario. We find that the answers received do yield useful insights for a well-designed LCS model and requirements for stakeholders to engage actively with an intelligent agent.<\/jats:p>","DOI":"10.1162\/artl_a_00414","type":"journal-article","created":{"date-parts":[[2023,8,23]],"date-time":"2023-08-23T15:29:02Z","timestamp":1692804542000},"page":"468-486","update-policy":"https:\/\/doi.org\/10.1162\/mitpressjournals.corrections.policy","source":"Crossref","is-referenced-by-count":6,"title":["Assessing Model Requirements for Explainable AI: A Template and Exemplary Case Study"],"prefix":"10.1162","volume":"29","author":[{"given":"Michael","family":"Heider","sequence":"first","affiliation":[{"name":"Universit\u00e4t Augsburg, Organic Computing Group. michael.heider@uni-a.de"}]},{"given":"Helena","family":"Stegherr","sequence":"additional","affiliation":[{"name":"Universit\u00e4t Augsburg, Organic Computing Group"}]},{"given":"Richard","family":"Nordsieck","sequence":"additional","affiliation":[{"name":"XITASO GmbH, IT & Software Solutions"}]},{"given":"J\u00f6rg","family":"H\u00e4hner","sequence":"additional","affiliation":[{"name":"Universit\u00e4t Augsburg, Organic Computing Group"}]}],"member":"281","published-online":{"date-parts":[[2023,11,1]]},"reference":[{"key":"2024020518220938300_bib1","doi-asserted-by":"publisher","first-page":"1757","DOI":"10.1145\/3520304.3533974","article-title":"The intersection of evolutionary computation and explainable AI","volume-title":"Proceedings of the Genetic and Evolutionary Computation conference companion","author":"Bacardit","year":"2022"},{"key":"2024020518220938300_bib2","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1007\/978-3-540-71231-2_5","article-title":"Bloat control and generalization pressure using the minimum description length principle for a Pittsburgh approach learning classifier system","volume-title":"Learning classifier systems","author":"Bacardit","year":"2007"},{"key":"2024020518220938300_bib3","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1016\/j.inffus.2019.12.012","article-title":"Explainable artificial intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI","volume":"58","author":"Barredo Arrieta","year":"2020","journal-title":"Information Fusion"},{"key":"2024020518220938300_bib4","doi-asserted-by":"publisher","DOI":"10.3389\/fdata.2021.688969","article-title":"Principles and practice of explainable machine learning","volume":"4","author":"Belle","year":"2021","journal-title":"Frontiers in Big Data"},{"key":"2024020518220938300_bib5","first-page":"905","article-title":"Accuracy based neuro and neuro-fuzzy classifier systems","volume-title":"Proceedings of the 4th annual conference on Genetic and Evolutionary Computation","author":"Bull","year":"2002"},{"key":"2024020518220938300_bib6","doi-asserted-by":"publisher","first-page":"102538","DOI":"10.1016\/j.ijinfomgt.2022.102538","article-title":"Stop ordering machine learning algorithms by their explainability! A user-centered investigation of performance and explainability","volume":"69","author":"Herm","year":"2022","journal-title":"International Journal of Information Management"},{"issue":"4","key":"2024020518220938300_bib7","doi-asserted-by":"publisher","first-page":"465","DOI":"10.1109\/TEVC.2013.2281537","article-title":"Reusing building blocks of extracted knowledge to solve complex, large-scale Boolean problems","volume":"18","author":"Iqbal","year":"2014","journal-title":"IEEE Transactions on Evolutionary Computation"},{"key":"2024020518220938300_bib8","doi-asserted-by":"publisher","first-page":"2270","DOI":"10.1109\/CEC.2006.1688588","article-title":"XCSF with neural prediction","volume-title":"2006 IEEE international conference on Evolutionary Computation","author":"Lanzi","year":"2006"},{"key":"2024020518220938300_bib9","doi-asserted-by":"publisher","first-page":"410","DOI":"10.1145\/3321707.3321719","article-title":"Absumption to complement subsumption in learning classifier systems","volume-title":"Proceedings of the Genetic and Evolutionary Computation Conference","author":"Liu","year":"2019"},{"issue":"3","key":"2024020518220938300_bib10","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1145\/3468166","article-title":"A comparison of learning classifier systems\u2019 rule compaction algorithms for knowledge visualization","volume":"1","author":"Liu","year":"2021","journal-title":"ACM Transactions on Evolutionary Learning and Optimization"},{"key":"2024020518220938300_bib11","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1007\/s11047-020-09840-0","article-title":"Visualizations for rule-based machine learning","volume":"21","author":"Liu","year":"2021","journal-title":"Natural Computing"},{"key":"2024020518220938300_bib12","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1016\/j.jprocont.2019.02.005","article-title":"Autonomous supervision and optimization of product quality in a multi-stage manufacturing process based on self-adaptive prediction models","volume":"76","author":"Lughofer","year":"2019","journal-title":"Journal of Process Control"},{"key":"2024020518220938300_bib13","doi-asserted-by":"publisher","first-page":"147","DOI":"10.1109\/ICMLA.2017.0-165","article-title":"An evolutionary learning approach to self-configuring image pipelines in the context of carbon fiber fault detection","volume-title":"2017 16th IEEE international conference on Machine Learning and Applications (ICMLA)","author":"Margraf","year":"2017"},{"key":"2024020518220938300_bib14","doi-asserted-by":"publisher","first-page":"417","DOI":"10.1016\/j.procir.2015.12.114","article-title":"Self-optimizing production systems","volume":"41","author":"Permin","year":"2016","journal-title":"Procedia CIRP"},{"key":"2024020518220938300_bib15","doi-asserted-by":"publisher","first-page":"1135","DOI":"10.1145\/2939672.2939778","article-title":"\u201cWhy should I trust you?\u201d: Explaining the predictions of any classifier","volume-title":"Proceedings of the 22nd ACM SIGKDD international conference on Knowledge Discovery and Data Mining","author":"Ribeiro","year":"2016"},{"key":"2024020518220938300_bib16","doi-asserted-by":"publisher","first-page":"5548","DOI":"10.1109\/IROS45743.2020.9341714","article-title":"Deep reinforcement learning for industrial insertion tasks with visual inputs and natural rewards","volume-title":"2020 IEEE\/RSJ international conference on Intelligent Robots and Systems (IROS)","author":"Schoettler","year":"2020"},{"key":"2024020518220938300_bib17","doi-asserted-by":"publisher","first-page":"1349","DOI":"10.1145\/3067695.3082488","article-title":"Toward curious learning classifier systems: Combining XCS with active learning concepts","volume-title":"Proceedings of the Genetic and Evolutionary Computation Conference Companion","author":"Stein","year":"2017"},{"key":"2024020518220938300_bib18","doi-asserted-by":"publisher","first-page":"110","DOI":"10.7551\/978-0-262-31709-2-ch017","article-title":"Rapid rule compaction strategies for global knowledge discovery in a supervised learning classifier system","volume-title":"ECAL 2013: The twelfth European conference on Artificial Life","author":"Tan","year":"2013"},{"issue":"4","key":"2024020518220938300_bib19","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1109\/MCI.2012.2215124","article-title":"An analysis pipeline with statistical and visualization-guided knowledge discovery for Michigan-style learning classifier systems","volume":"7","author":"Urbanowicz","year":"2012","journal-title":"IEEE Computational Intelligence Magazine"},{"key":"2024020518220938300_bib20","doi-asserted-by":"publisher","first-page":"Article 736398","DOI":"10.1155\/2009\/736398","article-title":"Learning classifier systems: A complete introduction, review, and roadmap","volume":"2009","author":"Urbanowicz","year":"2009","journal-title":"Journal of Artificial Evolution and Applications"},{"issue":"2","key":"2024020518220938300_bib21","doi-asserted-by":"publisher","first-page":"737","DOI":"10.1109\/TII.2016.2618892","article-title":"Agent and cyber-physical system based self-organizing and self-adaptive intelligent shopfloor","volume":"13","author":"Zhang","year":"2017","journal-title":"IEEE Transactions on Industrial Informatics"}],"container-title":["Artificial Life"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/direct.mit.edu\/artl\/article-pdf\/29\/4\/468\/2328348\/artl_a_00414.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/direct.mit.edu\/artl\/article-pdf\/29\/4\/468\/2328348\/artl_a_00414.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,5]],"date-time":"2024-02-05T18:22:22Z","timestamp":1707157342000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/artl\/article\/29\/4\/468\/117306\/Assessing-Model-Requirements-for-Explainable-AI-A"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":21,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2023,11,1]]},"published-print":{"date-parts":[[2023,11,1]]}},"URL":"https:\/\/doi.org\/10.1162\/artl_a_00414","relation":{},"ISSN":["1064-5462","1530-9185"],"issn-type":[{"value":"1064-5462","type":"print"},{"value":"1530-9185","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2023]]},"published":{"date-parts":[[2023]]}}}