[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-122528-en":3,"doc-seo-122528-105":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},122528,1099514068365,"Aurelia","https://ap-avatar.wpscdn.com/avatar/10000253d8d9f28188e?_k=1776742907772140068",8,"Research & Report","Commercial Shop Price Assessment - Comparing Machine Learning and Ordinary Least Squares for Improved Accuracy","This study compares the predictive performance of Ordinary Least Squares (OLS) and five machine learning (ML) algorithms for valuing commercial shop properties, using 2,480 transactions from Kuala Lumpur spanning 2013 to 2023. OLS delivers limited predictive power, while Random Forest with log-transformed target variables achieves substantially higher accuracy (R² = 0.9974, RMSE = 0.03, MAPE = 0.02%). Results validate ML as a reliable, efficient, and scalable alternative for property valuation, improving precision in commercial real estate assessment.","University of Westminster, London, UK, 29-31 Aug 2025  \nCommercial Shop Price Assessment: Comparing Machine Learning and Ordinary Least Squares for improved accuracy  \nJunainah Mohamad1*, Intan Faiqah Hamizah Mohd Firazan1, Suraya Masrom2, Abdul Rehman Gilal3  \n*Corresponding Author  \n1 Department of Built Environment Studies and Technology, Faculty of Built Environment, Universiti Teknologi MARA, Perak Branch, Seri Iskandar Campus, Malaysia  \n2 Faculty of Computer and Mathematical Sciences, Universiti Teknologi MARA, Perak Branch, Tapah Campus, Malaysia  \n3 Knight Foundation School of Computing and Information Sciences, Florida International University, USA  \n[mjunainah@uitm.edu.my](mjunainah@uitm.edu.my), [intanfaiqahhamizah@gmail.com](intanfaiqahhamizah@gmail.com), [suray078@uitm.edu.my](suray078@uitm.edu.my), [arehman@fiu.edu](arehman@fiu.edu)  \nTel: +60127123044  \nAbstract  \nThis study compares the predictive performance of OLS and five ML algorithms in valuing commercial shop properties using 2,480 transactions from Kuala Lumpur from 2013 to 2023. While OLS showed limited predictive power, the Random Forest algorithm, applied with log-transformed target variables, achieved superior accuracy (R² = 0.9974, RMSE = 0.03, MAPE = 0.02%) . These findings support the use of machine learning as a reliable and efficient alternative for property valuation, offering enhanced precision and scalability in commercial real estate assessment.  \nKeywords: Commercial Valuation; Machine Learning; Random Forest; Ordinary Least Squares  \neISSN: 2398-4287 © 2025. The Authors. Published forAMER by e-International Publishing House, Ltd., UK. This is an open access article under the CC BY-NC-ND license ([http://creativecommons.org/licenses/by-nc-nd/4.0/](http://creativecommons.org/licenses/by-nc-nd/4.0/)). Peer–review under responsibility ofAMER (Association of Malaysian Environment-Behaviour Researchers).  \nDOI: [https://doi.org/10.21834/e-bpj.v10i33.7256](https://doi.org/10.21834/e-bpj.v10i33.7256)  \n1.0 Introduction  \nAccurate valuation of commercial properties is fundamental to the functioning of real estate markets, as it shapes investment decisions, guides urban planning, and informs policymaking (Malpezzi, 2003) . In rapidly growing cities such as Kuala Lumpur, Malaysia, the expansion of commercial activity and rising demand for retail space intensify the need for robust and reliable valuation models that can reflect market realities (Topraklı, 2025; Khamis et al. , 2020) . Commercial shops, in particular, represent a vital segment of the urban property market, directly influencing business development, municipal revenue, and the broader urban economy. Thus, precise and data-driven valuation of these assets is critical to sustaining balanced urban growth and investor confidence.  \nTraditionally, the Ordinary Least Squares (OLS) regression model , also known as the Hedonic Pricing Model (HPM), has been the dominant tool for property valuation, explaining property prices based on structural, locational, and neighbourhood attributes (Abidoye & Chan, 2018) . While OLS is valued for its simplicity and interpretability, it is limited by sensitivity to functional form assumptions, multicollinearity, and the inability to capture nonlinear interactions common in complex real estate datasets (Selim, 2009; Bourassa et al. , 2025) . While hedonic models can be specified in linear, semi-log, or log-log forms, the choice of the most suitable functional form often presents methodological challenges (Owusu-Ansah, 2018), reducing forecasting accuracy and consistency.  \nIn response to these limitations, Machine Learning (ML) methods have emerged as powerful alternatives, representing what Breiman (2001) describes as the algorithmic modelling culture. Algorithms such as Decision Trees, Random Forests, Support Vector Regression, and XGBoost can capture nonlinear relationships, high-dimensional interactions, and complex patterns often overlooked by OLS  \n(Anti","cbCaiagrqzFQky1Z","https://ap.wps.com/l/cbCaiagrqzFQky1Z","pdf",916388,1,9,"English","en",105,"# Introduction\n## Problem background and significance\n## Traditional OLS/Hedonic Pricing Model\n## Motivation for machine learning methods\n## Study aim and objectives\n# Literature Review\n## Operational definition of shop","[{\"question\":\"What data and time period were used to compare OLS and ML for commercial shop valuation?\",\"answer\":\"The study uses 2,480 commercial shop transactions from Kuala Lumpur covering 2013 to 2023 to compare predictive performance.\"},{\"question\":\"How did OLS perform compared with machine learning models?\",\"answer\":\"OLS showed limited predictive power, whereas the Random Forest model achieved much higher accuracy when the target variable was log-transformed.\"},{\"question\":\"Which ML approach produced the best results, and what metrics were reported?\",\"answer\":\"Random Forest provided the strongest performance with log-transformed targets, reporting R² = 0.9974, RMSE = 0.03, and MAPE = 0.02%.\"}]","Commercial Shop Price Assessment - Comparing Machine Learning and Ordinary Least Squares for Improved Accuracy | PDF",1785811107,23,{"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},"commercial-shop-price-assessment-comparing-machine-learning-and-ordinary-least-squares-for-improved-accuracy","",{"@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/commercial-shop-price-assessment-comparing-machine-learning-and-ordinary-least-squares-for-improved-accuracy/122528/",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",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What data and time period were used to compare OLS and ML for commercial shop valuation?","Question",{"text":75,"@type":76},"The study uses 2,480 commercial shop transactions from Kuala Lumpur covering 2013 to 2023 to compare predictive performance.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How did OLS perform compared with machine learning models?",{"text":80,"@type":76},"OLS showed limited predictive power, whereas the Random Forest model achieved much higher accuracy when the target variable was log-transformed.",{"name":82,"@type":73,"acceptedAnswer":83},"Which ML approach produced the best results, and what metrics were reported?",{"text":84,"@type":76},"Random Forest provided the strongest performance with log-transformed targets, reporting R² = 0.9974, RMSE = 0.03, and MAPE = 0.02%.","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},[93,97,101,105,110,115,120,123,127,130,134],{"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":121,"slug":122},30,"research-report",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},"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"]