[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-117798-en":3,"doc-seo-117798-105":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},117798,687197100911,"Himbo","https://ap-avatar.wpscdn.com/avatar/a000239b6f1da00475?x-image-process=image/resize,m_fixed,w_180,h_180&k=1785132997149421697",8,"Research & Report","Machine learning reduces soft costs for residential solar photovoltaics","Residential solar photovoltaics deployment depends on lowering soft (non-hardware) costs, especially customer acquisition expenses that are larger and harder to reduce than hardware costs. This study replaces significance-based methods with prediction-oriented models to identify PV adopters and non-adopters. Using machine learning, the true positive rate for adopters rises from 66% to 87% and the true negative rate for non-adopters from 75% to 88%, outperforming logistic regression. Improved prediction reduces customer acquisition costs by 15% and helps reveal market expansion opportunities while informing broader clean-energy adoption and related policy challenges.","Lawrence Berkeley National Laboratory LBL Publications  \nTitle  \nMachine learning reduces soft costs for residential solar photovoltaics  \nPermalink  \n[https://escholarship.org/uc/item/2815b47r](https://escholarship.org/uc/item/2815b47r)  \nJournal  \nScientific Reports, 13(1)  \nISSN  \n2045-2322  \nAuthors  \nDong, Changgui  \nNemet, Gregory Gao, Xue et al.  \nPublication Date  \n2023-05-01  \nDOI  \n10.1038/s41598-023-33014-4  \nCopyright Information  \nThis work is made available under the terms of a Creative Commons AttributionNonCommercial-NoDerivatives License, available at [https://creativecommons.org/licenses/by-nc-nd/4.0/](https://creativecommons.org/licenses/by-nc-nd/4.0/)  \nPeer reviewed  \n[eScholarship.org](eScholarship.org) Powered by the California Digital Library  \nUniversity of California  \n[www. nature.com/scientificreports](www. nature.com/scientificreports)  \nOPEN  \nMachine learning reduces soft costs for residential solar photovoltaics  \nChanggui Dong1*, Gregory Nemet2, Xue Gao3,4*, Galen Barbose 5, Benjamin Sigrin6 & Eric O’Shaughnessy7  \nFurther deployment of rooftop solar photovoltaics (PV) hinges on the reduction of soft (non-hardware) costs—now larger and more resistant to reductions than hardware costs. The largest portion of these soft costs is the expenses solar companies incur to acquire new customers. In this study, we demonstrate the value of a shift from significance-based methodologies to prediction-oriented models to better identify PV adopters and reduce soft costs. We employ machine learning to predict PV adopters and non-adopters, and compare its prediction performance with logistic regression, the dominant significance-based method in technology adoption studies. Our results show that machine learning substantially enhances adoption prediction performance: The true positive rate of predicting adopters increased from 66 to 87%, and the true negative rate of predicting non-adopters increased from 75 to 88%. We attribute the enhanced performance to complex variable interactions and nonlinear effects incorporated by machine learning. With more accurate predictions, machine learning is able to reduce customer acquisition costs by 15%($0.07/Watt) and identify new market opportunities for solar companies to expand and diversify their customer bases. Our research methods and findings provide broader implications for the adoption of similar clean energy technologies and related policy challenges such as market growth and energy inequality.  \nDeploying renewable energy technologies is key to mitigating climate change and fostering an energy transition1–3. Driven by rapid hardware cost reductions, solar photovoltaics (PV) is ready to be subsidy-free and power a sustainable future4,5. However, PV non-hardware or “soft” costs now account for over 60% of installed prices and are more resistant to reductions than hardware costs6. Soft cost stagnation could slow PV diffusion7–9. Customer acquisition costs, i.e., PV companies’ costs to identify and acquire new customers, are currently the largest component of PV soft costs. Customer acquisition costs amounted to 21%($0.43/Watt) of total PV soft costs in the U.S. in 202010. Furthermore, customer acquisition costs have been rising as rooftop solar diffusion shifts from early adopters to mass diffusion, and as customers get fatigue from door-to-door marketing, creating a substantial challenge for PV companies10, 11. Developing efficient and effective methods to identify prospective PV adopters could reduce customer acquisition costs, accelerating technology diffusion and the associated climate benefits. Improved adoption prediction could also benefit grid infrastructure planning, transmission and storage siting, and subsidy policy design for low-income communities via adoption ‘seeding’12.  \nPredicting household PV adoption differs from explaining PV adoption. Prior research has relied on significance-based methods with an extensive focus on the differences between PV ad","cbCaiu5vourfSayK","https://ap.wps.com/l/cbCaiu5vourfSayK","pdf",2038964,1,15,"English","en",105,"# Background and problem definition\n## Soft costs and customer acquisition costs\n## Limits of significance-based adoption research\n# Methods and modeling approach\n## Prediction-oriented machine learning framework\n## Comparison with logistic regression\n# Results and implications\n## Adoption prediction performance improvements\n## Cost reduction and market opportunities\n## Broader implications for clean energy policy","[{\"question\":\"Why focus on “soft costs” in residential solar photovoltaics?\",\"answer\":\"Soft costs, especially customer acquisition expenses, account for over 60% of installed prices and are more resistant to hardware cost reductions.\"},{\"question\":\"How does the study improve PV adopter identification?\",\"answer\":\"It uses prediction-oriented machine learning models to predict adopters and non-adopters, rather than relying on significance-based methods that search for statistically significant differences.\"},{\"question\":\"What impact does machine learning have on customer acquisition costs?\",\"answer\":\"More accurate predictions reduce customer acquisition costs by 15% (about $0.07/Watt) and help identify new market opportunities for solar companies.\"}]","Machine learning reduces soft costs for residential solar photovoltaics | PDF",1785679630,38,{"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-reduces-soft-costs-for-residential-solar-photovoltaics","",{"@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-reduces-soft-costs-for-residential-solar-photovoltaics/117798/",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},"Why focus on “soft costs” in residential solar photovoltaics?","Question",{"text":76,"@type":77},"Soft costs, especially customer acquisition expenses, account for over 60% of installed prices and are more resistant to hardware cost reductions.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How does the study improve PV adopter identification?",{"text":81,"@type":77},"It uses prediction-oriented machine learning models to predict adopters and non-adopters, rather than relying on significance-based methods that search for statistically significant differences.",{"name":83,"@type":74,"acceptedAnswer":84},"What impact does machine learning have on customer acquisition costs?",{"text":85,"@type":77},"More accurate predictions reduce customer acquisition costs by 15% (about $0.07/Watt) and help identify new market opportunities for solar companies.","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"]