[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-120104-en":3,"doc-seo-120104-105":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":20,"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},120104,8796095462418,"Noah","https://ap-avatar.wpscdn.com/avatar/80000253c1241d02b47?x-image-process=image/resize,m_fixed,w_180,h_180&k=1778826106357471780",8,"Research & Report","Feature Importance and Explainability in Quantum Machine Learning - Comparison Study","Feature importance and explainability address the black-box nature of many machine learning models by improving transparency and trust, especially in high-stakes domains such as healthcare and finance. This work studies how these insights carry over to Quantum Machine Learning (QML), leveraging quantum-mechanical capabilities like superposition. Using the Iris dataset, classical SVM and Random Forests are compared with IBM Qiskit-based hybrid models (VQC and QSVC), applying permutation and leave-one-out feature importance plus ALE and SHAP explainers to contrast model-derived inferences.","Feature Importance and Explainability in Quantum  \nMachine Learning  \nLuke Power1 , Krishnendu Guha2  \nSchool of Computer Science and Information Technology, University College Cork, Ireland Email: [120371316@umail.ucc.ie](120371316@umail.ucc.ie1)[1](120371316@umail.ucc.ie1) (corresponding author), [kguha@ucc.ie](kguha@ucc.ie2)[2](kguha@ucc.ie2)  \narXiv :2405 .08917v1 [ cs .LG] 14 May 2024  \nAbstract—Many Machine Learning (ML) models are referred to as black-box models, providing no real insights into why a prediction is made. Feature importance and explainability are important for increasing transparency and trust in ML models, particularly in settings such as healthcare and finance. With quantum computing’s unique capabilities, such as leveraging quantum mechanical phenomena like superposition, this can be combined with ML techniques to create the field of Quantum Machine Learning (QML), and such techniques may be applied to QML models. This article explores feature importance and explainability insights in QML compared to Classical ML models. Utilizing the widely recognized Iris dataset, classical ML algorithms— SVM and Random Forests, are compared against hybrid quantum counterparts, implemented via IBM’s Qiskit platform: the Variational Quantum Classifier (VQC) and Quantum Support Vector Classifier (QSVC). This article aims to provide an in-depth comparison of the insights generated in ML by employing permutation and leave-one-out feature importance methods, alongside ALE (Accumulated Local Effects) and SHAP (SHapley Additive exPlanations) explainers.  \nIndex Terms—ML, QML, Feature Importance, Explainability  \nI. INTRODUCTION  \nThis article aims to provide an understanding of quantum computing, and how it takes quantum mechanical phenomenon and integrates with classical machine learning to facilitate quantum machine learning (QML), alongwith explainability. Given how many current ML models are considered ’blackbox’ or ’opaque models’, meaning that there is no real way to understand how or why an output is generated, there is a rise in the necessity to implement ways of explaining a models inner workings and rationalising its outputs. Currently, there are several methodologies to determine a model’s most important features and explainability of individual predictions, and this article seeks to apply these methods to QML models and make an in-depth comparison of the results.  \nA. Objectives  \nThe main objective of this article is to ascertain what new inferences could be made about a dataset via QML when compared to ML and attempt to explain how these differences come about. For this article, we are interested in using classical data, but quantum algorithms, in another way; the top-right quadrant of the image 1 . This was achieved by using a common ML method, building an equivalent QML model, and making inferences about the data by measuring feature importance-i.e. how important a feature is in making an accurate classification by using feature omission and permutations  \nto quantify the differences, and also applying explainability methods to the models, which can provide greater insights into a singular prediction.  \nAs of writing, this paper is the first to provide a comprehensive comparison of the results of applying machine learning explainability to QML on multi-class data.  \nThis article will also delve into the theory behind quantum computing and the implementations of some basic quantum computing models to give clear demonstrations of the ’quantum advantage’.  \nFig. 1: Classical Data on Quantum Algorithms. We are using Classical data with Quantum algorithms. Image adapted from  \n[1] .  \nB. Work Overview  \nThe rest of the Introduction will provide a general overview of the article; the main objectives as well as some theoretical background on the main concepts of quantum computing and ML and a brief overview of the primary technology and tools that were used over the course of completing this article. Chapter Two, T","cbCaijXVnTj6AGGF","https://ap.wps.com/l/cbCaijXVnTj6AGGF","pdf",4809002,1,23,"English","en",105,"# Introduction\n## Objectives\n## Work Overview\n## Overview of Methodology\n# Background\n## Concepts and Technologies","[{\"question\":\"Why are feature importance and explainability important in machine learning?\",\"answer\":\"Many ML models behave like black boxes, giving little insight into why predictions are made. Feature importance and explainability improve transparency and help build trust in model outputs.\"},{\"question\":\"Which datasets and models are compared in the study?\",\"answer\":\"The study uses the Iris dataset and compares classical ML models (SVM, Random Forests) with hybrid quantum models implemented in IBM Qiskit (VQC, QSVC).\"},{\"question\":\"What methods are used to measure feature importance and explain predictions?\",\"answer\":\"The paper applies permutation and leave-one-out feature importance, and uses ALE (Accumulated Local Effects) and SHAP (SHapley Additive exPlanations) explainers for interpretability of predictions.\"}]","Feature Importance and Explainability in Quantum Machine Learning - Comparison Study | PDF",1785728216,58,{"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},"feature-importance-and-explainability-in-quantum-machine-learning-comparison-study","",{"@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/feature-importance-and-explainability-in-quantum-machine-learning-comparison-study/120104/",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","2026-08-03",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why are feature importance and explainability important in machine learning?","Question",{"text":75,"@type":76},"Many ML models behave like black boxes, giving little insight into why predictions are made. Feature importance and explainability improve transparency and help build trust in model outputs.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which datasets and models are compared in the study?",{"text":80,"@type":76},"The study uses the Iris dataset and compares classical ML models (SVM, Random Forests) with hybrid quantum models implemented in IBM Qiskit (VQC, QSVC).",{"name":82,"@type":73,"acceptedAnswer":83},"What methods are used to measure feature importance and explain predictions?",{"text":84,"@type":76},"The paper applies permutation and leave-one-out feature importance, and uses ALE (Accumulated Local Effects) and SHAP (SHapley Additive exPlanations) explainers for interpretability of predictions.","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},[93,97,101,105,110,115,120,123,128,131,135],{"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":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]