[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-126044-en":3,"doc-seo-126044-105":31,"detail-sidebar-cat-0-en-105":93},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":28,"seo_description":14,"update_tm":29,"read_time":30},126044,962084928904,"Asher","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","XMLPO - An Ontology for Explainable Machine Learning Pipeline","Machine Learning models often function as black boxes, offering limited transparency into how decisions are formed. Explainable Artificial Intelligence (XAI) targets this gap by clarifying the rationale behind model outputs and improving trustworthiness. This paper presents XMLPO, an extension of the Explainable ML Workflows ontology, implemented in OWL and built upon ML-Schema. XMLPO strengthens feature categorization, enriches data pre-processing and metadata, and expands XAI approach and metric representation, supported by a manufacturing case study.","Formal Ontology in Information Systems  \nC. Trojahn et al. (Eds.)  \n© 2024 The Authors.  \nThis article is published online with Open Access by IOS Press and distributed under the terms of the Creative Commons Attribution Non-Commercial License 4.0 (CC BY-NC 4.0). doi:10.3233/FAIA241306  \n193  \nXMLPO: An Ontology for Explainable Machine Learning Pipeline  \nDonika XHANI a, 1 , Joo Luiz REBELO MOREIRAb , Marten VAN SINDEREN b and  \nLu´ıs FERREIRA PIRES b  \na IEBIS group, BMS Faculty, University of Twente bSCS group, EEMCS Faculty, University of Twente  \nORCiD ID: Donika Xhani [https://orcid.org/0000-0003-2536-0574](https://orcid.org/0000-0003-2536-0574), Joo Luiz Rebelo Moreira [https://orcid.org/0000-0002-4547-7000](https://orcid.org/0000-0002-4547-7000), Marten van Sinderen [https://orcid.org/0000-0001-7118-1353](https://orcid.org/0000-0001-7118-1353), Lu´ıs Ferreira Pires [https://orcid.org/0000-0001-7432-7653](https://orcid.org/0000-0001-7432-7653)  \nAbstract. Machine Learning (ML) models often operate as black-boxes, lacking transparency in their decision-making processes. Explainable Artificial Intelligence (XAI) aims to address the rationale behind these decisions, thereby enhancing the trustworthiness of ML models. In this paper, we propose an extension of the Explainable ML Workflows ontology, which was designed as a reference ontology with OntoUML, and implemented as an operational ontology with OWL. The Explainable ML workflows ontology reuses ML-Schema, which is a core ontology for representing ML algorithms. We have identified four main issues in the conceptualization of this ontology, namely the lack of feature categorization, the lack of data pre-processing methods, the shallow description of metadata related to training and testing, and the lack of detailed representation of XAI approaches and metrics. We addressed these four issues in the so-called Explainable ML Pipeline Ontology (XMLPO), which aims to provide a comprehensive description of the ML pipeline for XAI. XMLPO offers a deeper understanding of the entire ML pipeline, encompassing data input, pre-processing, model training and testing, and explanation processes. XMLPO was validated through a case study on the prediction of specific performance indicators in a manufacturing company, and the results of this validation showed that the ontology helps data scientists to better comprehend a  \nML pipeline and the features that influence the ML prediction model the most.  \nKeywords. Ontology, Explainable AI (XAI), Machine Learning pipeline, Semantics  \n1. Introduction  \nOrganizations are increasingly turning to Machine Learning (ML) models to develop predictive or classification models for their data [1] . However, especially when these models are based on complex structures like neural networks or deep learning they are commonly referred to as black-boxes due to their inherent opacity. The lack of transparency in black-box ML models makes it difficult for their users to understand why the model predicts or classifies certain outcomes, and to correct erroneous feature selections, cre-  \n1 Corresponding Author: Donika Xhani, [d.xhani@utwente.nl](d.xhani@utwente.nl)  \n194 D. Xhani et al. / XMLPO: An Ontology for Explainable Machine Learning Pipeline  \nating uncertainty about the reliability of the predictions and classifications [2,3] . Moreover, the complexity inherent in these black-box models poses significant challenges for humans to comprehend the reasoning and methods behind their outcomes [5,6] .  \nExplainable Artificial Intelligence (XAI) encompasses methods and techniques designed to make ML models explicable, interpretable, transparent, and understandable for humans [7] . Understanding ML models is crucial as it enables users to recognize necessary adjustments in data pre-processing, model training, and testing procedures when the output is incorrect [8,9] . As stated by Adadi and Berrada (p. 52155,[10]): “It is not enough to just explain the model, the user has to","cbCaiih0Ot3eRk5n","https://ap.wps.com/l/cbCaiih0Ot3eRk5n","pdf",5968848,7,1,15,"English","en",105,"# Introduction\n## Problem of black-box ML and need for XAI\n## Role of ontologies in defining ML pipeline semantics\n## Limitations of the prior Explainable ML Workflows ontology\n# Goal and contributions of XMLPO\n## Extension scope: data, model, evaluation, and XAI representation","[{\"question\":\"What problem does XAI address in machine learning models?\",\"answer\":\"XAI addresses the opacity of black-box ML models by making their decision-making rationale more transparent and understandable to humans.\"},{\"question\":\"What does XMLPO extend compared with the earlier Explainable ML Workflows ontology?\",\"answer\":\"XMLPO extends it by improving feature categorization, adding richer data pre-processing and metadata, detailing model-related components, and expanding the representation of XAI approaches and metrics.\"},{\"question\":\"How was XMLPO validated and what were the results?\",\"answer\":\"XMLPO was validated using a case study predicting performance indicators in a manufacturing company. Results showed that the ontology helps data scientists better understand the ML pipeline and the features most influencing the predictions.\"}]","XMLPO - An Ontology for Explainable Machine Learning Pipeline | PDF",1785902715,38,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":88,"head_meta":90,"extra_data":92,"updated_unix":29},"xmlpo-an-ontology-for-explainable-machine-learning-pipeline","",{"@graph":37,"@context":87},[38,55,70],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,49,52],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":48},"https://docshare.wps.com/document/","Document",2,{"item":50,"name":12,"@type":44,"position":51},"https://docshare.wps.com/document/research-report/",3,{"item":53,"name":13,"@type":44,"position":54},"https://docshare.wps.com/document/xmlpo-an-ontology-for-explainable-machine-learning-pipeline/126044/",4,{"url":53,"name":13,"@type":56,"author":57,"headline":13,"publisher":59,"fileFormat":62,"inLanguage":24,"description":14,"dateModified":63,"datePublished":64,"encodingFormat":62,"isAccessibleForFree":65,"interactionStatistic":66},"DigitalDocument",{"name":9,"@type":58},"Person",{"url":42,"name":60,"@type":61},"DocShare","Organization","application/pdf","2026-08-25","2026-08-05",true,{"@type":67,"interactionType":68,"userInteractionCount":20},"InteractionCounter",{"@type":69},"ViewAction",{"@type":71,"mainEntity":72},"FAQPage",[73,79,83],{"name":74,"@type":75,"acceptedAnswer":76},"What problem does XAI address in machine learning models?","Question",{"text":77,"@type":78},"XAI addresses the opacity of black-box ML models by making their decision-making rationale more transparent and understandable to humans.","Answer",{"name":80,"@type":75,"acceptedAnswer":81},"What does XMLPO extend compared with the earlier Explainable ML Workflows ontology?",{"text":82,"@type":78},"XMLPO extends it by improving feature categorization, adding richer data pre-processing and metadata, detailing model-related components, and expanding the representation of XAI approaches and metrics.",{"name":84,"@type":75,"acceptedAnswer":85},"How was XMLPO validated and what were the results?",{"text":86,"@type":78},"XMLPO was validated using a case study predicting performance indicators in a manufacturing company. Results showed that the ontology helps data scientists better understand the ML pipeline and the features most influencing the predictions.","https://schema.org",{"og:url":53,"og:type":89,"og:title":13,"og:site_name":60,"og:description":14},"article",{"robots":91,"canonical":53},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":94},[95,99,103,107,112,117,121,124,129,132,136],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":96,"show_sort_weight":97,"slug":98},"Story & Novel",90,"story-novel",{"id":48,"doc_module":4,"doc_module_name":47,"category_name":100,"show_sort_weight":101,"slug":102},"Literature",80,"literature",{"id":54,"doc_module":4,"doc_module_name":47,"category_name":104,"show_sort_weight":105,"slug":106},"Exam",70,"exam",{"id":108,"doc_module":4,"doc_module_name":47,"category_name":109,"show_sort_weight":110,"slug":111},5,"Comic",60,"comic",{"id":113,"doc_module":4,"doc_module_name":47,"category_name":114,"show_sort_weight":115,"slug":116},6,"Technology",50,"technology",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":118,"show_sort_weight":119,"slug":120},"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":47,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":47,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":47,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":47,"category_name":138,"show_sort_weight":108,"slug":139},19,"General","general"]