[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-118539-en":3,"doc-seo-118539-105":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},118539,962075114101,"Seraphina","https://ap-avatar.wpscdn.com/avatar/e000253a75eb197efd?x-image-process=image/resize,m_fixed,w_180,h_180&k=1780044092746381165",8,"Research & Report","Sustainable Portfolio Construction via Machine Learning - ESG, SDG and Sentiment","This study proposes portfolio construction strategies based on novel sentiment, ESG and SDG scores. It uses natural language processing to build a daily sentiment score system that reduces concerns arising from different rating standards. Portfolios are optimized monthly with machine learning models using daily historical returns, and performance is evaluated against equal-weighted benchmarks in SPX500 and STOXX600. Nonlinear methods, including random forests, neural networks, and genetic algorithms, show superior portfolio management results.","European Financial Management  \nEUROPEAN FINANCIAL MANAGEMENT  \n ORIGINAL ARTICLE   \nSustainable Portfolio Construction via Machine Learning: ESG, SDG and Sentiment  \nXin Feng1 | Hans‐Jörg von Mettenheim2 | Georgios Sermpinis1 | Charalampos Stasinakis1  \n1University of Glasgow, Adam Smith Business School, University of Glasgow, Glasgow, UK | 2IPAG Business School, Paris, France Correspondence: Charalampos Stasinakis ([Charalampos.Stasinakis@glasgow.ac.uk](Charalampos.Stasinakis@glasgow.ac.uk))  \nReceived: 18 April 2024 | Revised: 4 October 2024 | Accepted: 24 October 2024  \nFunding: The authors received no specific funding for this work.  \nKeywords: ESG | machine learning | portfolio construction | SDG | sentiment indicators  \nABSTRACT  \nThis study proposes portfolio construction strategies based on novel sentiment, ESG and SDG scores. We utilize natural language processing to establish a novel daily score system that mitigates concerns of different rating standards. The portfolios constructed are optimized via machine learning algorithms on a monthly basis using daily historical returns. Utilizing the equal‐weighted portfolios as benchmarks, we empirically show that our optimized portfolios exhibit better trading performance in both the SPX500 and STOXX600 indices. The findings demonstrate that nonlinear models such as random forests, neural networks, and genetic algorithms can perform better than other machine learning models in portfolio management.  \nJEL Classification: F3, G11  \n1 | Introduction  \nThe concept of sustainability has gained significant attraction globally, prompting various stakeholders, such as businesses, governments, and generally society, to implement diverse innovative approaches. The prominence of sustainability and technological advancement has resulted in the emergence of Environmental, Social, and corporate Governance (ESG) as a crucial metric for assessing the sustainable profile of stocks in the capital markets1. Corporate Social Responsibility (CSR) is commonly perceived as a criterion for firms to attain sustainability and numerous academic studies have demonstrated its significant role in financial management (Edmans 2011; Lins, Servaes, and Tamayo 2017; Feng, Chen, and Tseng 2018) . A significant portion of the prior research has examined the correlation between CSR and financial performance2. Our study focuses on the development of portfolios utilizing daily sustainability indicators, as well as the incorporation of sentiment index and machine learning methodologies to address the demands of processing large data volumes.  \nThis paper is motivated by three dimensions of the literature. First, the application of the sentiment index in financial investment is experiencing an upward trend. The Efficient Market Hypothesis (EMH) proposed by Fama (1970) suggests that stock price in the market incorporates all pertinent information in a timely, accurate, and comprehensive manner. However, several studies explain that in the stock market, investors' behaviour has greater heterogeneity, resulting in abnormal returns that cannot be explained by traditional financial theories (Kumar, Page, and Spalt 2013). Therefore, most scholars consider investors' sentiment in financial investment as an important factor. Several researchers have attempted empirical frameworks to investigate this topic, and many of them find a positive relationship between current investor sentiment and future stock returns (Gao, Gu, and Koedijk 2021). Our study focuses on trading performance of portfolios constructed through equal‐weighted stock selection based on the top sentiment scores (Gillam, Guerard, and Cahan 2015).  \nSecond, corporate sustainability is also extensive and multidimensional depending on the measures used from researchers,  \nThis is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is prope","cbCaiuRZQVywiElW","https://ap.wps.com/l/cbCaiuRZQVywiElW","pdf",475977,1,22,"English","en",105,"# Introduction\n## Sustainability and ESG as a capital-markets metric\n## Sentiment in financial investment and market behavior\n## Links among ESG, CSR, and SDG","[{\"question\":\"What is the core goal of this study?\",\"answer\":\"To construct investment portfolios using newly developed sentiment, ESG and SDG scores, and to optimize them with machine learning for improved trading performance.\"},{\"question\":\"How are the daily sentiment scores created?\",\"answer\":\"Natural language processing is used to establish a daily score system that mitigates issues caused by differences across rating standards.\"},{\"question\":\"Which machine learning approaches outperform other models in portfolio management?\",\"answer\":\"Nonlinear models such as random forests, neural networks, and genetic algorithms perform better than other machine learning models in the reported portfolio results.\"}]","Sustainable Portfolio Construction via Machine Learning - ESG, SDG and Sentiment | PDF",1785684048,55,{"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},"sustainable-portfolio-construction-via-machine-learning-esg-sdg-and-sentiment","",{"@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/sustainable-portfolio-construction-via-machine-learning-esg-sdg-and-sentiment/118539/",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","2026-08-02",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 is the core goal of this study?","Question",{"text":75,"@type":76},"To construct investment portfolios using newly developed sentiment, ESG and SDG scores, and to optimize them with machine learning for improved trading performance.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How are the daily sentiment scores created?",{"text":80,"@type":76},"Natural language processing is used to establish a daily score system that mitigates issues caused by differences across rating standards.",{"name":82,"@type":73,"acceptedAnswer":83},"Which machine learning approaches outperform other models in portfolio management?",{"text":84,"@type":76},"Nonlinear models such as random forests, neural networks, and genetic algorithms perform better than other machine learning models in the reported portfolio results.","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"]