[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-116926-en":3,"doc-seo-116926-105":30,"detail-sidebar-cat-0-en-105":91},{"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":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},116926,962075006959,"Anda","https://ap-avatar.wpscdn.com/avatar/e0002397efbe92a78e?_k=1776741047341049297",8,"Research & Report","On the Integration of Interpretable Machine Learning Techniques to Machine Learning Pipeline - Dissertation","Machine learning models achieve superhuman results but remain opaque, limiting verification and auditability. This opacity becomes critical when regulations such as the GDPR require interpretability, especially in highly regulated domains where understanding explanations supports high-stakes decisions. This dissertation integrates interpretable machine learning techniques into each step of an ML pipeline to make models more transparent, actionable, and methodically usable. Contributions address industrial interpretability challenges, performance degradation from class imbalance in resampling, and SHAP-driven improvements in post-processing through reduced false positives and negatives.","PhD-FSTM-2023-061  \nFaculty of Science, Technology and Medicine  \nDISSERTATION  \nPresented on the 26/06/2023 in Luxembourg  \nto obtain the degree of  \nDOCTEUR DE L’UNIVERSITÉ DU LUXEMBOURG EN  \nINFORMATIQUE  \nby  \nYusuf Arslan  \nOn the Integration of Interpretable Machine Learning Techniques to Machine Learning Pipeline  \nDissertation Defense Committee  \nDr. Michail Papadakis, Chair  \nAssociate Professor, University of Luxembourg, Luxembourg  \nDr. Kevin Allix, Vice-chair  \nAssistant Professor, CentraleSupélec, France  \nDr. Jacques Klein, Supervisor  \nFull Professor, University of Luxembourg, Luxembourg  \nDr. Christin Seifert, Member  \nFull Professor, University of Marburg, Germany Dr. Benoît Frénay, Member  \nAssociate Professor, University of Namur, Belgium  \nDr. Maxime Cordy, Expert  \nResearch Scientist, University of Luxembourg, Luxembourg  \nAbstract  \nThe long history of machine learning (ML) has led to ML models with superhuman results. As a consequence of the superhuman results of ML models, more and more real-world application domains exploit them. However, ML models have disadvantages like opaqueness. In the absence of verification, an opaque black box model is left in the lurch. In addition, when regulations - such as the General Data Protection Regulation in Europe-apply, ML models need to be interpretable. These disadvantages and regulations cause under-use of ML models in highly regulated domains, especially when auditability of processes is demanded, and model understanding is crucial because of high stakes decisions.  \nInterpretable ML offers a solution to the drawbacks of ML models. It constitutes one of the main instruments that is available to practitioners. If interpretable ML can help practitioners to understand a model better, it could also help algorithms. Indeed, if humans are able to leverage information in explanations of interpretable ML techniques, such information may be methodically exploited in an automated setting. To confirm our intuition, we integrate interpretable ML techniques to the steps of ML pipelines.  \nThis dissertation makes the following contributions to the community:  \nThe first contribution of this thesis is to pinpoint the challenges of interpretable ML in the context of industrial implementation, provide recommendation to overcome these challenges, and thus illuminate the promising research directions as a result of the inspection of an industrial machine learning pipeline.  \nThe second contribution of this thesis is to offer a solution to the issue of ML model performance degradation caused by class imbalance in the resampling step of the model construction stage of the ML pipeline.  \nThe third contribution of this thesis is to highlight the potential of SHAP Explanations to improve model performance, especially for false-positive reduction to decrease the workload of experts while increasing customer trust in industrial settings by inspecting the output of the interpretation step of the post-processing stage of the ML pipeline.  \nThe final contribution of this thesis is to reduce both false-positives and falsenegatives by utilizing a second-step classifier based on the SHAP features by using the output of interpretation step of the post-processing stage to obtain a second model for the modeling step of the model construction stage of the ML pipeline.  \nii  \nThe eye of the Sea is one thing and the foam another. Let the foam go, and gaze with the eye of the Sea . Day and night foam-flecks are flung from the sea: oh amazing! You behold the foam but not the Sea . We are like boats dashing together; our eyes are darkened, yet we are in clear water.  \nMevlana Rumi  \niv  \nAcknowledgements  \nThis work has been supported by the Luxembourg National Research Fund (FNR) under the project ExLiFT (13778825) .  \nThis research would not have been possible without the help and support of the many people that I have met throughout my research. I would like to send my deepest gratitude each one of ","cbCaiq0NQtW9bcsu","https://ap.wps.com/l/cbCaiq0NQtW9bcsu","pdf",166243,1,12,"English","en",105,"# Abstract\n## Interpretable ML challenges and rationale\n## Integration across the ML pipeline\n## Contributions and research outcomes","[{\"question\":\"Why does interpretability matter for machine learning models in real-world use?\",\"answer\":\"Opaque models hinder verification and auditability. In regulated contexts such as those governed by GDPR, interpretability is required to support model understanding for high-stakes decisions.\"},{\"question\":\"How does the dissertation integrate interpretable machine learning into an ML pipeline?\",\"answer\":\"It integrates interpretable ML techniques into the steps of the ML pipeline so that explanation information can be leveraged by practitioners and exploited systematically in automated settings.\"},{\"question\":\"What contributions does the dissertation make regarding performance and errors?\",\"answer\":\"It addresses performance degradation caused by class imbalance in the resampling step and shows how SHAP explanations can improve performance by reducing false positives. It also proposes a second-step classifier using SHAP features to reduce both false positives and false negatives.\"}]","On the Integration of Interpretable Machine Learning Techniques to Machine Learning Pipeline - Dissertation | PDF",1785672570,30,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"on-the-integration-of-interpretable-machine-learning-techniques-to-machine-learning-pipeline-dissertation","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"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":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/on-the-integration-of-interpretable-machine-learning-techniques-to-machine-learning-pipeline-dissertation/116926/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-02",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why does interpretability matter for machine learning models in real-world use?","Question",{"text":75,"@type":76},"Opaque models hinder verification and auditability. In regulated contexts such as those governed by GDPR, interpretability is required to support model understanding for high-stakes decisions.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the dissertation integrate interpretable machine learning into an ML pipeline?",{"text":80,"@type":76},"It integrates interpretable ML techniques into the steps of the ML pipeline so that explanation information can be leveraged by practitioners and exploited systematically in automated settings.",{"name":82,"@type":73,"acceptedAnswer":83},"What contributions does the dissertation make regarding performance and errors?",{"text":84,"@type":76},"It addresses performance degradation caused by class imbalance in the resampling step and shows how SHAP explanations can improve performance by reducing false positives. It also proposes a second-step classifier using SHAP features to reduce both false positives and false negatives.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":29,"slug":121},"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":106,"slug":137},19,"General","general"]