{"title":"基于ESG评分的债券发行预测","authors":"Mingxuan Zhao, Hao Wu, Le Liu, Xiping Mao","doi":"10.25236/ajms.2023.040309","DOIUrl":null,"url":null,"abstract":": With the rising focus on low-carbon initiatives, interest in sustainable products and services, including cap-and-trade policies, green bonds, and low-carbon stocks, has surged. This study comprehensively investigates how Environmental, Social, and Governance (ESG) scores influence bond issuance. Employing state-of-the-art research methods and techniques, we ensure data quality through preprocessing, including handling missing values and normalization. Our predictive model, powered by machine learning algorithms such as linear regression, KNNR, XGB, and LGBM, adeptly captures relationships and handles high-dimensional features. Feature engineering further enhances model performance. Rigorous cross-validation and evaluation metrics like RMSE, MAE, and R2 ensure objectivity. Our research offers valuable insights for investors, issuers, and regulators in sustainable finance decision-making.","PeriodicalId":372277,"journal":{"name":"Academic Journal of Mathematical Sciences","volume":"124 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Forecast of bond issuance based on ESG score\",\"authors\":\"Mingxuan Zhao, Hao Wu, Le Liu, Xiping Mao\",\"doi\":\"10.25236/ajms.2023.040309\",\"DOIUrl\":null,\"url\":null,\"abstract\":\": With the rising focus on low-carbon initiatives, interest in sustainable products and services, including cap-and-trade policies, green bonds, and low-carbon stocks, has surged. This study comprehensively investigates how Environmental, Social, and Governance (ESG) scores influence bond issuance. Employing state-of-the-art research methods and techniques, we ensure data quality through preprocessing, including handling missing values and normalization. Our predictive model, powered by machine learning algorithms such as linear regression, KNNR, XGB, and LGBM, adeptly captures relationships and handles high-dimensional features. Feature engineering further enhances model performance. Rigorous cross-validation and evaluation metrics like RMSE, MAE, and R2 ensure objectivity. Our research offers valuable insights for investors, issuers, and regulators in sustainable finance decision-making.\",\"PeriodicalId\":372277,\"journal\":{\"name\":\"Academic Journal of Mathematical Sciences\",\"volume\":\"124 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"1900-01-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Academic Journal of Mathematical Sciences\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.25236/ajms.2023.040309\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Academic Journal of Mathematical Sciences","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.25236/ajms.2023.040309","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
: With the rising focus on low-carbon initiatives, interest in sustainable products and services, including cap-and-trade policies, green bonds, and low-carbon stocks, has surged. This study comprehensively investigates how Environmental, Social, and Governance (ESG) scores influence bond issuance. Employing state-of-the-art research methods and techniques, we ensure data quality through preprocessing, including handling missing values and normalization. Our predictive model, powered by machine learning algorithms such as linear regression, KNNR, XGB, and LGBM, adeptly captures relationships and handles high-dimensional features. Feature engineering further enhances model performance. Rigorous cross-validation and evaluation metrics like RMSE, MAE, and R2 ensure objectivity. Our research offers valuable insights for investors, issuers, and regulators in sustainable finance decision-making.