[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-118298-en":3,"doc-seo-118298-105":30,"detail-sidebar-cat-0-en-105":92},{"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},118298,7971461740909,"Levi","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","Machine Learning as a Service (MLaaS) Selection with Incomplete QoS Information","Machine learning as a Service (MLaaS) delivers machine-learning capabilities through Edge and Cloud Computing, making it attractive for long-term adoption by large organizations such as healthcare and research facilities. Since MLaaS offerings combine functional aspects (models on cloud resources) with non-functional Quality of Service (QoS) attributes, selecting the best service is critical. The selection challenge arises because providers often provide incomplete QoS details and hide latent features like explainability and intrinsic bias, reducing decision accuracy. This work presents a B-XAI-based approach to discover latent bias and explainability, construct a QoS profile from advertisements and experiences, and perform preference selection using the nearest-neighbour algorithm.","Association for Information Systems  \nAIS Electronic Library (AISeL)  \n\n| ACIS 2023 Proceedings | Australasian (ACIS) |\n| --- | --- |\n| 12-2-2023\u003Cbr>Machine Learning as a Service (MLaaS) Selection Incomplete QoS Information\u003Cbr>Keya Patel\u003Cbr>Curtin University, Australia, [k.patel38@postgrad.curtin.edu.au](k.patel38@postgrad.curtin.edu.au)\u003Cbr>Sajib Mistry\u003Cbr>Curtin University, Australia, [sajib.mistry@curtin.edu.au](sajib.mistry@curtin.edu.au)\u003Cbr>Sai Krishna Deepak Kanneganti\u003Cbr>Curtin University, Australia, [s.kanneganti@postgrad.curtin.edu.au](s.kanneganti@postgrad.curtin.edu.au)\u003Cbr>Aneesh Krishna\u003Cbr>Curtin University, Australia, [a.krishna@curtin.edu.au](a.krishna@curtin.edu.au)\u003Cbr>Follow this and additional works at: [https://aisel.aisnet.org/acis2023](https://aisel.aisnet.org/acis2023) | with |\n\nRecommended Citation  \nPatel, Keya; Mistry, Sajib; Kanneganti, Sai Krishna Deepak; and Krishna, Aneesh, \"Machine Learning as a Service (MLaaS) Selection with Incomplete QoS Information\" (2023) . ACIS 2023 Proceedings. 39.  \n[https://aisel.aisnet.org/acis2023/39](https://aisel.aisnet.org/acis2023/39)  \nThis material is brought to you by the Australasian (ACIS) at AIS Electronic Library (AISeL) . It has been accepted for inclusion in ACIS 2023 Proceedings by an authorized administrator of AIS Electronic Library (AISeL) . For more information, please [contact elibrary@aisnet.org](contact elibrary@aisnet.org).  \nMachine Learning as a Service (MLaaS) Selection with Incomplete QoS Information  \nFull research paper  \nKeya Patel  \nSchool of Elec Eng, Comp and Math Sci (EECMS) Curtin University  \nPerth, Western Australia  \nEmail: [16861963@student.curtin.edu.au](16861963@student.curtin.edu.au)  \nSajib Mistry  \nSchool of Elec Eng, Comp and Math Sci (EECMS) Curtin University  \nPerth, Western Australia  \nEmail: [sajib.mistry@curtin.edu.au](sajib.mistry@curtin.edu.au)  \nSai Krishna Deepak Kanneganti  \nSchool of Elec Eng, Comp and Math Sci (EECMS) Curtin University  \nPerth, Western Australia  \nEmail: [s.kanneganti@curtin.edu.au](s.kanneganti@curtin.edu.au)  \nAneesh Krishna  \nSchool of Elec Eng, Comp and Math Sci (EECMS) Curtin University  \nPerth, Western Australia [Email: ](Email: A.Krishna@curtin.edu.au)[A.Krishna@curtin.edu.au](Email: A.Krishna@curtin.edu.au)  \nAbstract  \nMachine learning as a Service (MLaaS) is a topical service paradigm that enables ML technologies to be leveraged as services using Edge and Cloud Computing. Many big organisations, such as health care and research facilities, use MLaaS services on along-term basis. As a result, selecting an ideal MLaaS service is a significant decision for long-term customers. A typical MLaaS service consists of functional and nonfunctional aspects. Functional attributes are ML models running on cloud resources, and non-functional attributes are the Quality of Service (QoS), such as response time, price, availability, bias, and explainability. These QoS attributes help customers to select the best MLaaS-performing services from many similar ones. The selection process is complicated as big MLaaS service providers provide incomplete information about the quality of services and accuracy and disclose latent QoS features such as explainability and intrinsic bias. We propose discovering latent features, bias and explainability using the B-XAI framework. We will build a complete profile of the QoSof MLaaS based on MLaaS advertisements, other user experiences, and trial experiences. After completing the QoS profile, we will make the preference selection with the help of the nearest neighbour algorithm.  \nKeywords (MLaaS, Machine Learning as a service, QoS attributes, non-functional attributes, nearest neighbour, Preference selection B-XAI)  \n1 Introduction  \nAs we gradually move towards the future, artificial intelligence with machine learning has become a game-changer in computing (Sahi 2022) . Machine learning (ML) is a subspecialty of Artificial Intelligence (AI) that is considered a most importa","cbCaiq575BNQUcEg","https://ap.wps.com/l/cbCaiq575BNQUcEg","pdf",550117,1,14,"English","en",105,"# Introduction\n## MLaaS and the selection problem\n## Functional vs non-functional attributes and QoS\n## Latent QoS features and proposed approach","[{\"question\":\"What makes MLaaS service selection difficult for long-term customers?\",\"answer\":\"MLaaS selection is complex because providers may share incomplete QoS information and may not disclose latent quality aspects that affect real-world performance and decision outcomes.\"},{\"question\":\"Which QoS attributes are considered in MLaaS offerings?\",\"answer\":\"QoS includes non-functional attributes such as response time, price, availability, bias, and explainability, which help differentiate between similar services.\"},{\"question\":\"How does the proposed B-XAI framework support preference selection?\",\"answer\":\"The framework discovers latent bias and explainability to build a complete QoS profile from MLaaS advertisements, other user experiences, and trial experiences, then applies a nearest-neighbour algorithm for preference selection.\"}]","Machine Learning as a Service (MLaaS) Selection with Incomplete QoS Information | PDF",1785682893,35,{"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":87,"head_meta":89,"extra_data":91,"updated_unix":28},"machine-learning-as-a-service-mlaas-selection-with-incomplete-qos-information","",{"@graph":36,"@context":86},[37,54,69],{"@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/machine-learning-as-a-service-mlaas-selection-with-incomplete-qos-information/118298/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-05","2026-08-02",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"What makes MLaaS service selection difficult for long-term customers?","Question",{"text":76,"@type":77},"MLaaS selection is complex because providers may share incomplete QoS information and may not disclose latent quality aspects that affect real-world performance and decision outcomes.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"Which QoS attributes are considered in MLaaS offerings?",{"text":81,"@type":77},"QoS includes non-functional attributes such as response time, price, availability, bias, and explainability, which help differentiate between similar services.",{"name":83,"@type":74,"acceptedAnswer":84},"How does the proposed B-XAI framework support preference selection?",{"text":85,"@type":77},"The framework discovers latent bias and explainability to build a complete QoS profile from MLaaS advertisements, other user experiences, and trial experiences, then applies a nearest-neighbour algorithm for preference selection.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":46,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":46,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":46,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":46,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":46,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]