[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-120603-en":3,"doc-seo-120603-105":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},120603,13056703020460,"Valentina","https://ap-avatar.wpscdn.com/avatar/be000253dac470eee5d?_k=1778207105932848923",8,"Research & Report","Predicting Corporate ESG Scores from Financial Performance and Environmental Indicators - A Machine Learning Framework","Growing climate concerns are accelerating the demand from investors, regulators, and the public for accurate Environmental, Social, and Governance (ESG) assessment beyond traditional methods. This study evaluates 1,000 firms across nine industries and seven regions from 2015–2025 to forecast overall ESG scores using financial and environmental indicators. A diverse machine-learning suite (Linear Regression, Random Forest, AdaBoost, LightGBM, XGBoost, CatBoost) is combined with a panel-aware GroupKFold cross-validation to reduce bias. Boosting models consistently outperform linear baselines, with CatBoost delivering the strongest accuracy (lowest RMSE 4.608, MAE 2.222, MSE 21.234; highest R² 0.913).","Munich Personal RePEc Archive  \nA machine learning framework for predicting corporate ESG scores from financial performance and environmental indicators  \nChouech, Olfa  \nFaculty of Economic Sciences and Management of Tunis, University of Tunis El Manar, Tunisia  \n1 September 2025  \nOnline at [https://mpra. ub. uni-muenchen. de/127272/](https://mpra. ub. uni-muenchen. de/127272/)  \n[MPRA Paper No. 127272](MPRA Paper No. 127272) , [posted 08 Feb 2026 07:28 UTC](posted 08 Feb 2026 07:28 UTC)  \nPredicting Corporate ESG Scores from Financial Performance and Environmental Indicators: A Machine Learning Framework  \nAuthor names: Olfa CHAOUECH  \nAffiliations: Faculty of Economic Sciences and Management of Tunis, University of Tunis El Manar, Tunisia  \nEmail: [chaouecholfa@gmail.com](chaouecholfa@gmail.com)  \nAbstract:  \nAs investors, regulators, and the public increasingly emphasize sustainable investment amid growing climate concerns, the accurate prediction of Environmental, Social, and Governance (ESG) metrics has become a crucial complement to traditional assessment methods. This study analyzes 1,000 companies across nine industries and seven regions between 2015 and 2025 to predict overall ESG scores using key financial and environmental indicators. To ensure robust predictive performance, a diverse set of machine learning algorithms—including Linear Regression, Random Forests, and four boosting models (AdaBoost, LightGBM, XGBoost, and CatBoost)—was employed. To address potential bias in panel data, a panel-aware machine learning framework incorporating GroupKFold cross-validation was implemented. The results show that boosting algorithms consistently outperform traditional linear approaches in predicting ESG scores. Among them, CatBoost achieved the best overall performance, with the lowest RMSE (4.608), MAE (2.222), and MSE (21.234), and the highest R² (0.913), indicating strong predictive accuracy. Overall, this study presents an innovative and transferable framework for predicting ESG scores, thus contributing to both empirical research and quantitative modeling practices. Furthermore, it advances the sustainability field by providing a machine learning–based application that enables companies to predict their ESG scores in real time.  \nKeywords: ESG, Machine Learning, Boosting Algorithms, Sustainable Development, Predictive Modeling  \n1. Introduction:  \nThe classical economic perspective posits that a firm’s primary objective is to maximize profits for its owners, a notion deeply rooted in Adam Smith’s concept of the “invisible hand”(Smith, 1776) and later crystallized by Milton Friedman’s shareholder value theory (Friedman, 1970) . However, despite its enduring influence, this doctrine has faced increasing challenge from those advocating that corporations should serve a broader societal purpose. This shift is codified in the stakeholder theory, which emphasizes that firms must consider a wider range of actors—including employees, customers, local communities, suppliers, and the natural environment—in their decision-making processes (Freeman, 1984; Donaldson & Preston, 1995) . In line with this expanded view of corporate responsibility, global initiatives and investor demand have driven the integration of Environmental, Social, and Governance (ESG) factors into mainstream finance. The launch of the United Nations Global Compact in 2000, which encourages firms to align operations with principles on human rights, labor, the environment, and anti-corruption, marked a key turning point. Concurrently, the “Who Cares Wins”1 initiative popularized ESG integration, emphasizing that firms prioritizing sustainability tend to exhibit greater resilience, operational efficiency, and stakeholder loyalty (Eccles et al., 2014; Friede et al., 2015) . Investor demand for sustainability information has since exploded, demonstrated by the fact that 98% of S&P 500 companies published ESG disclosures in 2022, a dramatic increase from only 20% in","cbCailmtwNP9jLgK","https://ap.wps.com/l/cbCailmtwNP9jLgK","pdf",1134580,1,29,"English","en",105,"# Introduction\n## Background: From shareholder value to stakeholder and ESG\n## Financial materiality and evidence from market stress\n## Practical challenges in measuring ESG performance\n# Methodology\n## Dataset and indicator selection\n## Machine learning models\n## Panel-aware validation with GroupKFold\n# Results\n## Model comparison and performance metrics\n## Best-performing algorithm and interpretation\n# Conclusion\n## Transferable ESG prediction framework and real-time application","[{\"question\":\"What problem does the document address regarding ESG assessment?\",\"answer\":\"It addresses the difficulty of making accurate, scalable predictions of Environmental, Social, and Governance (ESG) metrics using financial and environmental indicators, given challenges in data collection and reporting consistency.\"},{\"question\":\"How is the prediction task set up in the study?\",\"answer\":\"The study analyzes 1,000 companies across nine industries and seven regions over 2015–2025 to predict overall ESG scores using selected financial and environmental indicators.\"},{\"question\":\"Which machine learning approach performs best and what evidence supports this?\",\"answer\":\"Boosting algorithms outperform linear models, and CatBoost achieves the best overall results with RMSE 4.608, MAE 2.222, MSE 21.234, and the highest R² of 0.913.\"}]","Predicting Corporate ESG Scores from Financial Performance and Environmental Indicators - A Machine Learning Framework | PDF",1785730853,73,{"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},"predicting-corporate-esg-scores-from-financial-performance-and-environmental-indicators-a-machine-learning-framework","",{"@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/predicting-corporate-esg-scores-from-financial-performance-and-environmental-indicators-a-machine-learning-framework/120603/",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","2026-08-03",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 problem does the document address regarding ESG assessment?","Question",{"text":75,"@type":76},"It addresses the difficulty of making accurate, scalable predictions of Environmental, Social, and Governance (ESG) metrics using financial and environmental indicators, given challenges in data collection and reporting consistency.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How is the prediction task set up in the study?",{"text":80,"@type":76},"The study analyzes 1,000 companies across nine industries and seven regions over 2015–2025 to predict overall ESG scores using selected financial and environmental indicators.",{"name":82,"@type":73,"acceptedAnswer":83},"Which machine learning approach performs best and what evidence supports this?",{"text":84,"@type":76},"Boosting algorithms outperform linear models, and CatBoost achieves the best overall results with RMSE 4.608, MAE 2.222, MSE 21.234, and the highest R² of 0.913.","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"]