[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-122342-en":3,"doc-seo-122342-105":30,"detail-sidebar-cat-0-en-105":83},{"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},122342,2336464648746,"Skyler","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Cost-Optimised Machine Learning Model Comparison for Predictive Maintenance","Predictive maintenance is essential for reducing industrial downtime and costs, yet real-world datasets frequently face class imbalance and require cost-sensitive evaluation because misclassification errors carry unequal penalties. This study uses the SCANIA Component X dataset to improve predictive maintenance with seven supervised machine learning algorithms, trained on time-series features produced by a sliding-window approach. A cost-sensitive metric matching SCANIA’s misclassification cost matrix evaluates performance. Downsampling, downsampling with SMOTETomek, and manual class weighting are tested, with downsampling proving most effective. Random Forest and SVM achieve high accuracy and low misclassification costs, and a voting ensemble further improves cost efficiency.","Article  \nCost-Optimised Machine Learning Model Comparison for Predictive Maintenance  \nYating Yang and Muhammad Zahid Iqbal *  \nAcademic Editor: Ahmed Abu-Siada  \nReceived: 6 May 2025  \nRevised: 12 June 2025  \nAccepted: 16 June 2025  \nPublished: 19 June 2025  \nCitation: Yang, Y.; Iqbal, M.Z.  \nCost-Optimised Machine Learning Model Comparison for Predictive Maintenance. Electronics 2025, 14, 2497 . [https://doi.org/10.3390/](https://doi.org/10.3390/)[ ](https://doi.org/10.3390/)electronics14122497  \nCopyright: © 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license ([https://creativecommons.org/](https://creativecommons.org/)[ ](https://creativecommons.org/)[licenses/by/4.0/](licenses/by/4.0/)) .  \nSchool of Computing, Engineering & Digital Technologies, Teesside University, Middlesbrough TS1 3BX, UK  \n* Correspondence: [zahid.iqbal@tees.ac.uk](zahid.iqbal@tees.ac.uk)  \nAbstract: Predictive maintenance is essential for reducing industrial downtime and costs, yet real-world datasets frequently encounter class imbalance and require cost-sensitive evaluation due to costly misclassification errors. This study utilises the SCANIA Component Xdataset to advance predictive maintenance through machine learning, employing seven supervised algorithms, Support Vector Machine, Random Forest, Decision Tree, K-Nearest Neighbours, Multi-Layer Perceptron, XGBoost, and LightGBM, trained on time-series features extracted via a sliding window approach. A bespoke cost-sensitive metric, aligned with SCANIA’s misclassification cost matrix, assesses model performance. Three imbalance mitigation strategies, downsampling, downsampling with SMOTETomek, and manual class weighting, were explored, with downsampling proving most effective. Random Forest and Support Vector Machine models achieved high accuracy and low misclassification costs, whilst a voting ensemble further enhanced cost efficiency. This research emphasises the critical role of cost-aware evaluation and imbalance handling, proposing an ensemble-based framework to improve predictive maintenance in industrial applications  \nKeywords: predictive maintenance; machine learning; class imbalance; cost-sensitive evaluation; ensemble learning; SCANIA Component X; classification  \n1. Introduction  \nAs a fundamental aspect of the industrial sector, maintenance plays a crucial role in production costs, making well-structured strategies essential to minimise unplanned downtime, reduce expenses, and extend the lifespan of industrial machinery [1] . As illustrated in Figure 1, the evolution of maintenance strategies has transitioned from reactive approaches, where failures were addressed only after their occurrence, to preventive methods based on scheduled interventions [1] . With the advent of sensor technologies and monitoring equipment, this progression led to the adoption of condition-based maintenance (CBM), where maintenance decisions are guided by actual equipment condition. This is followed by predictive maintenance (PdM), which is widely used today, using the integration of IoT, machine learning, big data, and other advanced technologies to predict equipment failures before they occur [2,3] .  \nDespite the advances in machine learning for PdM, developing predictive models that are both accurate and cost-efficient remains a challenge particularly when applied to real-world industrial datasets. These datasets are often imbalanced, with failure cases representing only a small fraction of the observations. In high-stakes environments, misclassification carries unequal consequences; some failures are far more costly than others. Conventional evaluation metrics such as accuracy and F1-score may therefore be insufficient to capture the real-world implications of model predictions. As such, there is a  \ngrowing need to use cost-aware evaluation frameworks and to rigorous","cbCaijU8zjg0toqA","https://ap.wps.com/l/cbCaijU8zjg0toqA","pdf",1466897,1,19,"English","en",105,"# Introduction\n## Research questions\n# Background\n## Predictive Maintenance (PdM) Approaches\n## Cost-sensitive evaluation and class imbalance (context)","[{\"question\":\"What models and approach improved cost efficiency?\",\"answer\":\"Random Forest and Support Vector Machine achieve high accuracy with low misclassification costs. Additionally, a voting ensemble further enhances cost efficiency beyond individual models.\"}]","Cost-Optimised Machine Learning Model Comparison for Predictive Maintenance | PDF",1785810116,48,{"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":78,"head_meta":80,"extra_data":82,"updated_unix":28},"cost-optimised-machine-learning-model-comparison-for-predictive-maintenance","",{"@graph":36,"@context":77},[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/cost-optimised-machine-learning-model-comparison-for-predictive-maintenance/122342/",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","2026-08-04",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71],{"name":72,"@type":73,"acceptedAnswer":74},"What models and approach improved cost efficiency?","Question",{"text":75,"@type":76},"Random Forest and Support Vector Machine achieve high accuracy with low misclassification costs. Additionally, a voting ensemble further enhances cost efficiency beyond individual models.","Answer","https://schema.org",{"og:url":52,"og:type":79,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":81,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":84},[85,89,93,97,102,107,112,115,120,123,127],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":86,"show_sort_weight":87,"slug":88},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":90,"show_sort_weight":91,"slug":92},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Exam",70,"exam",{"id":98,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},5,"Comic",60,"comic",{"id":103,"doc_module":4,"doc_module_name":46,"category_name":104,"show_sort_weight":105,"slug":106},6,"Technology",50,"technology",{"id":108,"doc_module":4,"doc_module_name":46,"category_name":109,"show_sort_weight":110,"slug":111},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":113,"slug":114},30,"research-report",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},9,"Religion & Spirituality",20,"religion-spirituality",{"id":118,"doc_module":4,"doc_module_name":46,"category_name":121,"show_sort_weight":118,"slug":122},"World Cup","world-cup",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":124,"slug":126},10,"Lifestyle","lifestyle",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":98,"slug":129},"General","general"]