[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-128257-en":3,"doc-seo-128257-105":30,"detail-sidebar-cat-0-en-105":90},{"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":11},128257,2336475104957,"Seraphina","https://ap-avatar.wpscdn.com/avatar/22000c4c6bd8a5076e1?x-image-process=image/resize,m_fixed,w_180,h_180&k=1787554080175789136",8,"Research & Report","Automated Approaches to Interpreting and Explaining Machine Learning Models - Research paper","This paper presents a novel framework that automates machine learning (ML) model interpretation and explainability across diverse applications, prioritizing transparency, trust, and human-centered decision support. Because complex models such as deep neural networks often remain difficult to interpret, their use in sensitive or regulated settings is constrained. Existing XAI methods are commonly post-hoc and struggle to scale for real-time or large-scale deployments. The proposed approach embeds explanation methods directly into model development via a modular pipeline.","Technological University Dublin  \nARROW@TU Dublin  \n\n| SAML-25 Workshop on Statistical and Machine Learning | Research Institutes/Centres/Groups |\n| --- | --- |\n| 2025-06-05\u003Cbr>Automated Approaches to Interpreting and Explaining Machine Learning Models\u003Cbr>Tilak Chandrashekar\u003Cbr>[x00229541@mytudublin. ie](x00229541@mytudublin. ie), [x00229541@mytudublin.ie](x00229541@mytudublin.ie)\u003Cbr>Tarry Singh\u003Cbr>Parthscan. io B. V., Assen,, [tarry.singh@deepkapha.ai](tarry.singh@deepkapha.ai)\u003Cbr>Maged Shaban\u003Cbr>Technological University Dublin, [maged.shaban@tudublin.ie](maged.shaban@tudublin.ie)\u003Cbr>Follow this and additional works at: [https://arrow.tudublin.ie/saml](https://arrow.tudublin.ie/saml)\u003Cbr> Part of the Statistics and Probability Commons |  |\n\nRecommended Citation  \nChandrashekar, Tilak; Singh, Tarry; and Shaban, Maged, \"Automated Approaches to Interpreting and Explaining Machine Learning Models\" (2025) . SAML-25 Workshop on Statistical and Machine Learning. 7.  \n[https://arrow.tudublin.ie/saml/7](https://arrow.tudublin.ie/saml/7)  \nThis Conference Paper is brought to you by the EUt+ Academic Press a free to read and publish press of the European University of Technology.  \nThis work is licensed under a Creative Commons Attribution-NonCommercial-Share Alike 4.0 International License.  \nAutomated Approaches to Interpreting and Explaining Machine  \nLearning Models  \nTilak Chandrashekar∗ School of Enterprise Computing and Digital Transformation, Technological University Dublin, D24FKT9 Dublin, Ireland [x00229541@mytudublin.ie](x00229541@mytudublin.ie)  \nTarry Singh  \nEarthscan.io B.V., Assen, The Netherlands  \nMaged Shaban  \nSchool of Enterprise Computing and Digital Transformation, Technological University Dublin, D24FKT9 Dublin, Ireland  \nAbstract  \nThis paper proposes a novel framework for automating ML model interpretation and explainability across different applications with an emphasis on transparency, trust, and human-centric decisionmaking assistance. Although ML models, particularly advanced structures such as deep neural networks, possess superior predictive powers, their interpretability tends to be obscure, and thus their application in sensitive or regulated domains is impeded. Current XAI techniques, though promising, tend to be post-hoc and are not scalable for real-time or large-scale deployments. This study addresses such concerns by presenting an automated, modular pipeline where interpretation techniques are embedded in the process of developing the ML model.  \nThe framework employs a hybrid approach where model-agnostic and model-specific explanation methods such as SHAP (Shapley Additive Explanations), LIME (Local Interpretable Model-agnostic Explanations), and integrated gradients are combined. These are embedded in a continuous learning platform to produce interpretable insights along with model predictions. The framework was evaluated using benchmarking datasets from domains such as healthcare, finance, and environmental monitoring to assess generalizability, fidelity of interpretability, and scalability.  \nEmpirical results demonstrate that the automatic pipeline consistently made accurate predictions (mean accuracy of 93%) simultaneously with producing interpretable explanations as expected by domain experts. Automatic attribution maps and rule-based summaries facilitated real-time insight generation with more than 60% reduced human effort in interpretation. Additionally, explainability fidelity metrics determined strong alignment between model behaviour and generated explanations. Ethical AI principles guided the research, and transparency, human oversight, and fairness were embedded at each stage. Automating interpretation, the framework allows stakeholders to inspect model decisions, enhancing trust, accountability, and compliance in high-stakes environments.  \nOverall, this work significantly enhances explainable AI operationalization with a scalable and ethics-based solution for interpretation automati","cbCaijM0hX0LesGX","https://ap.wps.com/l/cbCaijM0hX0LesGX","pdf",965775,4,1,3,"English","en",105,"# Abstract\n# Introduction\n## The black-box interpretability challenge\n## Background on LIME and SHAP\n## Adding interpretability to training\n## Gaps motivating automated, scalable explanations","[{\"question\":\"What problem does the proposed framework address?\",\"answer\":\"It automates ML model interpretation and explainability to improve transparency and trust, especially where current post-hoc XAI techniques are not scalable for real-time or large-scale use.\"},{\"question\":\"Which explanation methods are integrated into the framework?\",\"answer\":\"The framework combines model-agnostic and model-specific techniques, including SHAP, LIME, and integrated gradients, to generate interpretable insights alongside predictions.\"},{\"question\":\"How was the framework evaluated and what were the results?\",\"answer\":\"It was evaluated on benchmarking datasets from healthcare, finance, and environmental monitoring, assessing generalizability, explanation fidelity, and scalability. Results report consistent accurate predictions with mean accuracy around 93%, plus reduced human effort and strong alignment between model behavior and explanations.\"}]","Automated Approaches to Interpreting and Explaining Machine Learning Models - Research paper | PDF",1785946275,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":85,"head_meta":87,"extra_data":89,"updated_unix":29},"automated-approaches-to-interpreting-and-explaining-machine-learning-models-research-paper","",{"@graph":36,"@context":84},[37,52,67],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,50],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":22},"https://docshare.wps.com/document/research-report/",{"item":51,"name":13,"@type":43,"position":20},"https://docshare.wps.com/document/automated-approaches-to-interpreting-and-explaining-machine-learning-models-research-paper/128257/",{"url":51,"name":13,"@type":53,"author":54,"headline":13,"publisher":56,"fileFormat":59,"inLanguage":24,"description":14,"dateModified":60,"datePublished":61,"encodingFormat":59,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":55},"Person",{"url":41,"name":57,"@type":58},"DocShare","Organization","application/pdf","2026-08-27","2026-08-05",true,{"@type":64,"interactionType":65,"userInteractionCount":20},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80],{"name":71,"@type":72,"acceptedAnswer":73},"What problem does the proposed framework address?","Question",{"text":74,"@type":75},"It automates ML model interpretation and explainability to improve transparency and trust, especially where current post-hoc XAI techniques are not scalable for real-time or large-scale use.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"Which explanation methods are integrated into the framework?",{"text":79,"@type":75},"The framework combines model-agnostic and model-specific techniques, including SHAP, LIME, and integrated gradients, to generate interpretable insights alongside predictions.",{"name":81,"@type":72,"acceptedAnswer":82},"How was the framework evaluated and what were the results?",{"text":83,"@type":75},"It was evaluated on benchmarking datasets from healthcare, finance, and environmental monitoring, assessing generalizability, explanation fidelity, and scalability. Results report consistent accurate predictions with mean accuracy around 93%, plus reduced human effort and strong alignment between model behavior and explanations.","https://schema.org",{"og:url":51,"og:type":86,"og:title":13,"og:site_name":57,"og:description":14},"article",{"robots":88,"canonical":51},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":91},[92,96,100,104,109,114,119,122,127,130,134],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":20,"doc_module":4,"doc_module_name":46,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":105,"doc_module":4,"doc_module_name":46,"category_name":106,"show_sort_weight":107,"slug":108},5,"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":105,"slug":137},19,"General","general"]