Corporate ESG rating prediction based on XGBoost-SHAP interpretable machine learning model
The prediction of corporate ESG ratings is of paramount importance in augmenting the scientific rigor and precision of ESG investment decisions and steering corporate management of ESG-related risks. While machine learning methodologies have been extensively utilized in forecasting corporate behavio...
Uloženo v:
| Vydáno v: | Expert systems with applications Ročník 295; s. 128809 |
|---|---|
| Hlavní autoři: | , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
Elsevier Ltd
01.01.2026
|
| Témata: | |
| ISSN: | 0957-4174 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | The prediction of corporate ESG ratings is of paramount importance in augmenting the scientific rigor and precision of ESG investment decisions and steering corporate management of ESG-related risks. While machine learning methodologies have been extensively utilized in forecasting corporate behavior, their deployment in corporate ESG ratings remains relatively nascent and is often criticized for a lack of interpretability. This study develops a predictive model for corporate ESG ratings using an XGBoost algorithm enhanced with SHAP interpretability. The methodological framework incorporates SMOTE-ENN for handling class imbalance and a comprehensive optimization approach utilizing 3-fold cross-validation and randomized hyperparameter search. The model incorporates a comprehensive set of 15 indicators spanning four critical dimensions—financial performance, environmental impact, social responsibility, and corporate governance, using a dataset of Chinese A-share listed companies from 2013 to 2022. The model’s predictive efficacy is subsequently elucidated, revealing that the XGBoost-SHAP framework achieves an accuracy and precision rate of 91.0% and 90.7%, respectively, with an F1-score and AUC value of 90.1% and 0.977, outperforming comparative models. The analysis underscores the significant influence of financial and non-financial factors on ESG rating predictions, with financial attributes exerting a relatively more pronounced impact than individual non-financial metrics. Tailored to the diverse objectives of ESG investors, this research further delineates a level definition model and a risk identification model, achieving predictive accuracies of 92.4% and 97.7%, respectively. The insights from this study furnish ESG investors with a robust foundation for enhancing investment outcomes and offer strategic guidance for corporations aiming to elevate their ESG performance. |
|---|---|
| AbstractList | The prediction of corporate ESG ratings is of paramount importance in augmenting the scientific rigor and precision of ESG investment decisions and steering corporate management of ESG-related risks. While machine learning methodologies have been extensively utilized in forecasting corporate behavior, their deployment in corporate ESG ratings remains relatively nascent and is often criticized for a lack of interpretability. This study develops a predictive model for corporate ESG ratings using an XGBoost algorithm enhanced with SHAP interpretability. The methodological framework incorporates SMOTE-ENN for handling class imbalance and a comprehensive optimization approach utilizing 3-fold cross-validation and randomized hyperparameter search. The model incorporates a comprehensive set of 15 indicators spanning four critical dimensions—financial performance, environmental impact, social responsibility, and corporate governance, using a dataset of Chinese A-share listed companies from 2013 to 2022. The model’s predictive efficacy is subsequently elucidated, revealing that the XGBoost-SHAP framework achieves an accuracy and precision rate of 91.0% and 90.7%, respectively, with an F1-score and AUC value of 90.1% and 0.977, outperforming comparative models. The analysis underscores the significant influence of financial and non-financial factors on ESG rating predictions, with financial attributes exerting a relatively more pronounced impact than individual non-financial metrics. Tailored to the diverse objectives of ESG investors, this research further delineates a level definition model and a risk identification model, achieving predictive accuracies of 92.4% and 97.7%, respectively. The insights from this study furnish ESG investors with a robust foundation for enhancing investment outcomes and offer strategic guidance for corporations aiming to elevate their ESG performance. |
| ArticleNumber | 128809 |
| Author | Zhao, Zexin Zhang, Jianfeng |
| Author_xml | – sequence: 1 givenname: Jianfeng orcidid: 0000-0003-4236-0242 surname: Zhang fullname: Zhang, Jianfeng email: 527802384@qq.com – sequence: 2 givenname: Zexin surname: Zhao fullname: Zhao, Zexin email: 1012352975@qq.com |
| BookMark | eNp9kE1LAzEQhnOoYFv9A57yB3ZNsp8BL7XUVigoVEG8hHzMaso2KUlQ_PfuUk8eepoXZp5h5pmhifMOELqhJKeE1rf7HOK3zBlhVU5Z2xI-QVPCqyYraVNeolmMe0JoQ0gzRe9LH44-yAR4tVvjIVj3gY8BjNXJeoeVjGDwEN7W997HlO02i2dsXYIwTCWpesAHqT-tA9yDDG7kD95Af4UuOtlHuP6rc_T6sHpZbrLt0_pxudhmumjKlLGWFIUB1fGuYbxui1rVStVSccU7zgpT0YqPbQ6FUoa0HSNSVR0DZgxvymKO2tNeHXyMATqhbZLj8SlI2wtKxOhF7MXoRYxexMnLgLJ_6DHYgww_56G7EwTDU18WgojagtODsgA6CePtOfwXiVOBzg |
| CitedBy_id | crossref_primary_10_1016_j_dajour_2025_100626 |
| Cites_doi | 10.3390/su16166979 10.1016/j.patrec.2005.10.010 10.1093/rof/rfac033 10.1145/2907070 10.1080/13547860.2023.2273017 10.1016/j.procs.2022.01.143 10.1145/2939672.2939785 10.3390/app13042272 10.1023/A:1010920819831 10.3390/s24041230 10.1108/K-12-2021-1289 10.1111/ecpo.12283 10.1007/s10203-021-00364-5 10.1051/e3sconf/202021402042 10.1002/for.3201 10.3390/math10244679 10.1002/csr.2746 |
| ContentType | Journal Article |
| Copyright | 2025 The Author(s) |
| Copyright_xml | – notice: 2025 The Author(s) |
| DBID | 6I. AAFTH AAYXX CITATION |
| DOI | 10.1016/j.eswa.2025.128809 |
| DatabaseName | ScienceDirect Open Access Titles Elsevier:ScienceDirect:Open Access CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Computer Science |
| ExternalDocumentID | 10_1016_j_eswa_2025_128809 S0957417425024273 |
| GroupedDBID | --K --M .DC .~1 0R~ 13V 1B1 1RT 1~. 1~5 4.4 457 4G. 5GY 5VS 6I. 7-5 71M 8P~ 9JN 9JO AAAKF AABNK AAEDT AAEDW AAFTH AAIKJ AAKOC AALRI AAOAW AAQFI AARIN AATTM AAXKI AAXUO AAYFN AAYWO ABBOA ABFNM ABJNI ABMAC ABMVD ABUCO ABUFD ACDAQ ACGFS ACHRH ACLOT ACNTT ACRLP ACVFH ACZNC ADBBV ADCNI ADEZE ADTZH AEBSH AECPX AEIPS AEKER AENEX AEUPX AFJKZ AFPUW AFTJW AGHFR AGUBO AGUMN AGYEJ AHHHB AHJVU AHZHX AIALX AIEXJ AIGII AIIUN AIKHN AITUG AKBMS AKRWK AKYEP ALEQD ALMA_UNASSIGNED_HOLDINGS AMRAJ ANKPU AOUOD APLSM APXCP AXJTR BJAXD BKOJK BLXMC BNSAS CS3 DU5 EBS EFJIC EFKBS EFLBG EO8 EO9 EP2 EP3 F5P FDB FIRID FNPLU FYGXN G-Q GBLVA GBOLZ HAMUX IHE J1W JJJVA KOM LG9 LY1 LY7 M41 MO0 N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. PQQKQ Q38 ROL RPZ SDF SDG SDP SDS SES SEW SPC SPCBC SSB SSD SSL SST SSV SSZ T5K TN5 ~G- ~HD 29G 9DU AAAKG AAQXK AAYXX ABKBG ABWVN ABXDB ACNNM ACRPL ADJOM ADMUD ADNMO AGQPQ ASPBG AVWKF AZFZN CITATION EJD FEDTE FGOYB G-2 HLZ HVGLF HZ~ R2- SBC SET WUQ XPP ZMT |
| ID | FETCH-LOGICAL-c374t-28033debf9f7296836b6bb6ab9b9f923d5159ebf99e3bbd08f20ab5f2e2dd9743 |
| ISICitedReferencesCount | 3 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001529393500003&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0957-4174 |
| IngestDate | Thu Nov 27 00:48:44 EST 2025 Tue Nov 18 20:42:36 EST 2025 Wed Dec 10 14:22:57 EST 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | XGBoost algorithm SHAP ESG rating prediction Machine learning |
| Language | English |
| License | This is an open access article under the CC BY license. |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c374t-28033debf9f7296836b6bb6ab9b9f923d5159ebf99e3bbd08f20ab5f2e2dd9743 |
| ORCID | 0000-0003-4236-0242 |
| OpenAccessLink | https://dx.doi.org/10.1016/j.eswa.2025.128809 |
| ParticipantIDs | crossref_citationtrail_10_1016_j_eswa_2025_128809 crossref_primary_10_1016_j_eswa_2025_128809 elsevier_sciencedirect_doi_10_1016_j_eswa_2025_128809 |
| PublicationCentury | 2000 |
| PublicationDate | 2026-01-01 |
| PublicationDateYYYYMMDD | 2026-01-01 |
| PublicationDate_xml | – month: 01 year: 2026 text: 2026-01-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationTitle | Expert systems with applications |
| PublicationYear | 2026 |
| Publisher | Elsevier Ltd |
| Publisher_xml | – name: Elsevier Ltd |
| References | Qi, Sun, Zheng, Qi (b0125) 2023; 45 Hand, Till (b0080) 2001; 45 Javier, De Mandojana Natalia, Raquel, Ivan (b0090) 2023; 26 Yan, Guanhua, Li, Liang (b0150) 2024; 1–9 Dong, Xue, Chen (b0070) 2023; 6 Kui, Meixuan, Jingyi, Xiaomeng, Gang (b0105) 2022; 199 Chen Tianqi & Guestrin Carlos (2016). XGBoost: A scalable tree boosting system. CoRR, abs/1603.02754. Yuxiao (b0165) 2023; 20 Al, Khedr, Magdi, Sakeena (b0015) 2023; 13 Branco, Torgo, Ribeiro (b0030) 2016; 49 David, Wang, Angel, Luo (b0065) 2024; 31 Zedda (b0170) 2024; 70 Aggarwal, Banerjee (b0010) 2024; 44 D’Amato, D’Ecclesia, Levantesi (b0050) 2021; 44 Lei, Ke, Huang, Sha (b0110) 2020; 214 Yi (b0155) 2023; 14 Mo, Zhang, Tan, Zhang, Guo (b0120) 2024 Aaron, Rodolphe, David, Samuel (b0005) 2016; 8 Wenlong (b0145) 2023; 30 Benyan, Ziqi, Yan (b0020) 2023; 227 Mehdary, Chehri, Jakimi, Saadane (b0115) 2024; 24 Jujie, Qian, Ying (b0095) 2023; 52 Fawcett (b0075) 2006; 27 Yicheng, Lianying, Yanna (b0160) 2019; 1325 David, Wang, Angel, Amjad (b0060) 2025; 30 Hongtao, Honghui, Wenqi, Huiying (b0085) 2023; 16 Berg, Kölbel, Rigobon (b0025) 2022; 26 Chowdhury, Mohammad Abdullah, Azad, Sulong, Nazmul Islam (b0045) 2023 Sun, Zeng, Ying, Yue, Xipu (b0130) 2024; 36 Jun, Wei, Zhuo, Dong (b0100) 2022 Zhuang, Hong (b0175) 2013; 08 Chen, Zhan, Li (b0040) 2020 D’Amato, D’Ecclesia, Levantesi (b0055) 2021; 19 Wang, Wang, Liu, Zhang, Jingde, Ma (b0140) 2024; 16 Surjeet, Bijeta, Magdalena, Carmen, Claudia (b0135) 2022; 10 Aggarwal (10.1016/j.eswa.2025.128809_b0010) 2024; 44 David (10.1016/j.eswa.2025.128809_b0060) 2025; 30 Chen (10.1016/j.eswa.2025.128809_b0040) 2020 Hongtao (10.1016/j.eswa.2025.128809_b0085) 2023; 16 D’Amato (10.1016/j.eswa.2025.128809_b0050) 2021; 44 Benyan (10.1016/j.eswa.2025.128809_b0020) 2023; 227 Dong (10.1016/j.eswa.2025.128809_b0070) 2023; 6 Wang (10.1016/j.eswa.2025.128809_b0140) 2024; 16 Jun (10.1016/j.eswa.2025.128809_b0100) 2022 Kui (10.1016/j.eswa.2025.128809_b0105) 2022; 199 Yi (10.1016/j.eswa.2025.128809_b0155) 2023; 14 Al (10.1016/j.eswa.2025.128809_b0015) 2023; 13 Mo (10.1016/j.eswa.2025.128809_b0120) 2024 Sun (10.1016/j.eswa.2025.128809_b0130) 2024; 36 D’Amato (10.1016/j.eswa.2025.128809_b0055) 2021; 19 Surjeet (10.1016/j.eswa.2025.128809_b0135) 2022; 10 Qi (10.1016/j.eswa.2025.128809_b0125) 2023; 45 10.1016/j.eswa.2025.128809_b0035 Hand (10.1016/j.eswa.2025.128809_b0080) 2001; 45 Jujie (10.1016/j.eswa.2025.128809_b0095) 2023; 52 Lei (10.1016/j.eswa.2025.128809_b0110) 2020; 214 Mehdary (10.1016/j.eswa.2025.128809_b0115) 2024; 24 David (10.1016/j.eswa.2025.128809_b0065) 2024; 31 Fawcett (10.1016/j.eswa.2025.128809_b0075) 2006; 27 Wenlong (10.1016/j.eswa.2025.128809_b0145) 2023; 30 Branco (10.1016/j.eswa.2025.128809_b0030) 2016; 49 Yuxiao (10.1016/j.eswa.2025.128809_b0165) 2023; 20 Aaron (10.1016/j.eswa.2025.128809_b0005) 2016; 8 Yan (10.1016/j.eswa.2025.128809_b0150) 2024; 1–9 Chowdhury (10.1016/j.eswa.2025.128809_b0045) 2023 Zhuang (10.1016/j.eswa.2025.128809_b0175) 2013; 08 Berg (10.1016/j.eswa.2025.128809_b0025) 2022; 26 Zedda (10.1016/j.eswa.2025.128809_b0170) 2024; 70 Javier (10.1016/j.eswa.2025.128809_b0090) 2023; 26 Yicheng (10.1016/j.eswa.2025.128809_b0160) 2019; 1325 |
| References_xml | – volume: 16 start-page: 6979 year: 2024 ident: b0140 article-title: A novel stacked generalization ensemble-based hybrid SGM-BRR model for ESG score prediction publication-title: Sustainability – volume: 31 start-page: 3468 year: 2024 end-page: 3486 ident: b0065 article-title: China's ESG scorecard: A predictive machine learning model publication-title: Corporate Social Responsibility and Environmental Management – volume: 1325 year: 2019 ident: b0160 article-title: Harsanyi-transformation oriented default risk prediction based on FA-XGBoost in P2P network loan publication-title: Journal of Physics Conference Series – start-page: 1 year: 2023 end-page: 25 ident: b0045 article-title: Environmental, social and governance (ESG) rating prediction using machine learning approaches publication-title: Annals of Operations Research – year: 2020 ident: b0040 article-title: Research on credit card transaction fraud prediction based on XGBoost algorithm model publication-title: Application Research of Computers – reference: Chen Tianqi & Guestrin Carlos (2016). XGBoost: A scalable tree boosting system. CoRR, abs/1603.02754. – volume: 70 year: 2024 ident: b0170 article-title: Credit scoring: Does XGboost outperform logistic regression? A test on Italian SMEs publication-title: Research in International Business and Finance – start-page: 2022 year: 2022 ident: b0100 article-title: Credit debt default risk assessment based on the XGBoost algorithm: An empirical study from China publication-title: Wireless Communications and Mobile Computing – volume: 26 start-page: 2 year: 2023 end-page: 10 ident: b0090 article-title: Connecting the sustainable development goals to firm-level sustainability and ESG factors: The need for double materiality publication-title: Business Research Quarterly – volume: 24 year: 2024 ident: b0115 article-title: Hyperparameter optimization with genetic algorithms and XGBoost: A step forward in smart grid fraud detection publication-title: Sensors – volume: 30 start-page: 779 year: 2023 end-page: 786 ident: b0145 article-title: Default prediction of internet finance users based on imbalance-XGBoost publication-title: Tehnički vjesnik – volume: 214 year: 2020 ident: b0110 article-title: An Xgboost based system for financial fraud detection publication-title: E3S Web of Conferences – volume: 45 start-page: 1934 year: 2023 end-page: 1943 ident: b0125 article-title: Prediction and analysis model for ground peak acceleration based on XGBoost and SHAP.Chinese publication-title: Journal of Geotechnical Engineering – volume: 13 start-page: 2272 year: 2023 ident: b0015 article-title: A powerful predicting model for financial statement fraud based on optimized XGBoost ensemble learning technique publication-title: Applied Sciences – volume: 199 start-page: 1128 year: 2022 end-page: 1135 ident: b0105 article-title: Research on personal credit risk evaluation based on XGBoost publication-title: Procedia Computer Science – volume: 44 start-page: 1 year: 2021 end-page: 24 ident: b0050 article-title: Fundamental ratios as predictors of ESG scores: A machine learning approach publication-title: Decisions in Economics and Finance – volume: 30 start-page: 128 year: 2025 end-page: 157 ident: b0060 article-title: ESG scoring and forecasting in China: advancing sustainable business with multidimensional modeling publication-title: Journal of the Asia Pacific Economy – volume: 20 start-page: 184 year: 2023 end-page: 188 ident: b0165 article-title: The impact of digital financial inclusion on corporate environmental performance publication-title: Statistics & Decision – volume: 26 start-page: 1315 year: 2022 end-page: 1344 ident: b0025 article-title: Aggregate confusion: The divergence of ESG ratings publication-title: Review of Finance – volume: 49 start-page: 1 year: 2016 end-page: 50 ident: b0030 article-title: A Survey of Predictive Modeling on Imbalanced Domains publication-title: ACM Computing Surveys (CSUR) – volume: 36 start-page: 1110 year: 2024 end-page: 1136 ident: b0130 article-title: An intelligent detecting model for financial frauds in Chinese A-share market publication-title: Economics & Politics – volume: 10 start-page: 4679 year: 2022 ident: b0135 article-title: Predicting fraud in financial payment services through optimized hyper-parameter-tuned XGBoost model publication-title: Mathematics – volume: 14 start-page: 2354 year: 2023 end-page: 2364 ident: b0155 article-title: Design of XGBoost prediction model for financial operation fraud of listed companies publication-title: International Journal of System Assurance Engineering and Management – volume: 45 start-page: 171 year: 2001 end-page: 186 ident: b0080 article-title: A simple generalisation of the area under the ROC curve for multiple class classification problems publication-title: Machine Learning – start-page: 1 year: 2024 end-page: 51 ident: b0120 article-title: Reassessment of corporate credit risk identification: novel discoveries from integrated machine learning models publication-title: Computational Economics – volume: 16 year: 2023 ident: b0085 article-title: ESG in China: A review of practice and research, and future research avenues publication-title: China Journal of Accounting Research – volume: 44 start-page: 339 year: 2024 end-page: 355 ident: b0010 article-title: Forecasting of S&P 500 ESG index by using CEEMDAN and LSTM approach publication-title: Journal of Forecasting – volume: 1–9 year: 2024 ident: b0150 article-title: Enterprise ESG indicator prediction model integrated with richness coordination technology publication-title: Journal of Computer Applications – volume: 52 start-page: 4158 year: 2023 end-page: 4177 ident: b0095 article-title: An XGBoost-based multivariate deep learning framework for stock index futures price forecasting publication-title: Kybernetes – volume: 08 start-page: 175 year: 2013 end-page: 176 ident: b0175 article-title: Research on the three-spiral measurement of government-industry-university-research in China based on patent data – also on the role of government in industry-university-research cooperation publication-title: Journal of Management World – volume: 8 start-page: 1597 year: 2016 end-page: 1614 ident: b0005 article-title: Do ratings of firms converge? Implications for managers, investors and strategy researchers publication-title: Strategic Management Journal – volume: 227 year: 2023 ident: b0020 article-title: The measurement and early warning of daily financial stability index based on XGBoost and SHAP: Evidence from China publication-title: Expert Systems with Applications – volume: 19 start-page: 1 year: 2021 end-page: 27 ident: b0055 article-title: ESG score prediction through random forest algorithm publication-title: Computational Management Science – volume: 6 year: 2023 ident: b0070 article-title: Analysis and comparison of loan default prediction models based on XGBoost and LightGBM algorithm publication-title: Academic Journal of Computing & Information Science – volume: 27 start-page: 861 year: 2006 end-page: 874 ident: b0075 article-title: An introduction to ROC analysis publication-title: Pattern Recognition Letters – volume: 14 start-page: 2354 issue: 6 year: 2023 ident: 10.1016/j.eswa.2025.128809_b0155 article-title: Design of XGBoost prediction model for financial operation fraud of listed companies publication-title: International Journal of System Assurance Engineering and Management – volume: 16 start-page: 6979 issue: 16 year: 2024 ident: 10.1016/j.eswa.2025.128809_b0140 article-title: A novel stacked generalization ensemble-based hybrid SGM-BRR model for ESG score prediction publication-title: Sustainability doi: 10.3390/su16166979 – volume: 19 start-page: 1 issue: 2 year: 2021 ident: 10.1016/j.eswa.2025.128809_b0055 article-title: ESG score prediction through random forest algorithm publication-title: Computational Management Science – start-page: 2022 year: 2022 ident: 10.1016/j.eswa.2025.128809_b0100 article-title: Credit debt default risk assessment based on the XGBoost algorithm: An empirical study from China publication-title: Wireless Communications and Mobile Computing – volume: 27 start-page: 861 issue: 8 year: 2006 ident: 10.1016/j.eswa.2025.128809_b0075 article-title: An introduction to ROC analysis publication-title: Pattern Recognition Letters doi: 10.1016/j.patrec.2005.10.010 – volume: 30 start-page: 779 issue: 3 year: 2023 ident: 10.1016/j.eswa.2025.128809_b0145 article-title: Default prediction of internet finance users based on imbalance-XGBoost publication-title: Tehnički vjesnik – volume: 227 year: 2023 ident: 10.1016/j.eswa.2025.128809_b0020 article-title: The measurement and early warning of daily financial stability index based on XGBoost and SHAP: Evidence from China publication-title: Expert Systems with Applications – volume: 26 start-page: 1315 issue: 6 year: 2022 ident: 10.1016/j.eswa.2025.128809_b0025 article-title: Aggregate confusion: The divergence of ESG ratings publication-title: Review of Finance doi: 10.1093/rof/rfac033 – start-page: 1 year: 2023 ident: 10.1016/j.eswa.2025.128809_b0045 article-title: Environmental, social and governance (ESG) rating prediction using machine learning approaches publication-title: Annals of Operations Research – volume: 49 start-page: 1 issue: 2 year: 2016 ident: 10.1016/j.eswa.2025.128809_b0030 article-title: A Survey of Predictive Modeling on Imbalanced Domains publication-title: ACM Computing Surveys (CSUR) doi: 10.1145/2907070 – volume: 30 start-page: 128 issue: 1 year: 2025 ident: 10.1016/j.eswa.2025.128809_b0060 article-title: ESG scoring and forecasting in China: advancing sustainable business with multidimensional modeling publication-title: Journal of the Asia Pacific Economy doi: 10.1080/13547860.2023.2273017 – start-page: 1 year: 2024 ident: 10.1016/j.eswa.2025.128809_b0120 article-title: Reassessment of corporate credit risk identification: novel discoveries from integrated machine learning models publication-title: Computational Economics – volume: 26 start-page: 2 issue: 1 year: 2023 ident: 10.1016/j.eswa.2025.128809_b0090 article-title: Connecting the sustainable development goals to firm-level sustainability and ESG factors: The need for double materiality publication-title: Business Research Quarterly – volume: 199 start-page: 1128 year: 2022 ident: 10.1016/j.eswa.2025.128809_b0105 article-title: Research on personal credit risk evaluation based on XGBoost publication-title: Procedia Computer Science doi: 10.1016/j.procs.2022.01.143 – ident: 10.1016/j.eswa.2025.128809_b0035 doi: 10.1145/2939672.2939785 – volume: 13 start-page: 2272 issue: 4 year: 2023 ident: 10.1016/j.eswa.2025.128809_b0015 article-title: A powerful predicting model for financial statement fraud based on optimized XGBoost ensemble learning technique publication-title: Applied Sciences doi: 10.3390/app13042272 – volume: 1–9 year: 2024 ident: 10.1016/j.eswa.2025.128809_b0150 article-title: Enterprise ESG indicator prediction model integrated with richness coordination technology publication-title: Journal of Computer Applications – volume: 45 start-page: 171 issue: 2 year: 2001 ident: 10.1016/j.eswa.2025.128809_b0080 article-title: A simple generalisation of the area under the ROC curve for multiple class classification problems publication-title: Machine Learning doi: 10.1023/A:1010920819831 – volume: 70 issue: PB year: 2024 ident: 10.1016/j.eswa.2025.128809_b0170 article-title: Credit scoring: Does XGboost outperform logistic regression? A test on Italian SMEs publication-title: Research in International Business and Finance – volume: 24 issue: 4 year: 2024 ident: 10.1016/j.eswa.2025.128809_b0115 article-title: Hyperparameter optimization with genetic algorithms and XGBoost: A step forward in smart grid fraud detection publication-title: Sensors doi: 10.3390/s24041230 – year: 2020 ident: 10.1016/j.eswa.2025.128809_b0040 article-title: Research on credit card transaction fraud prediction based on XGBoost algorithm model publication-title: Application Research of Computers – volume: 1325 year: 2019 ident: 10.1016/j.eswa.2025.128809_b0160 article-title: Harsanyi-transformation oriented default risk prediction based on FA-XGBoost in P2P network loan publication-title: Journal of Physics Conference Series – volume: 8 start-page: 1597 year: 2016 ident: 10.1016/j.eswa.2025.128809_b0005 article-title: Do ratings of firms converge? Implications for managers, investors and strategy researchers publication-title: Strategic Management Journal – volume: 52 start-page: 4158 issue: 10 year: 2023 ident: 10.1016/j.eswa.2025.128809_b0095 article-title: An XGBoost-based multivariate deep learning framework for stock index futures price forecasting publication-title: Kybernetes doi: 10.1108/K-12-2021-1289 – volume: 08 start-page: 175 year: 2013 ident: 10.1016/j.eswa.2025.128809_b0175 article-title: Research on the three-spiral measurement of government-industry-university-research in China based on patent data – also on the role of government in industry-university-research cooperation publication-title: Journal of Management World – volume: 36 start-page: 1110 issue: 2 year: 2024 ident: 10.1016/j.eswa.2025.128809_b0130 article-title: An intelligent detecting model for financial frauds in Chinese A-share market publication-title: Economics & Politics doi: 10.1111/ecpo.12283 – volume: 16 issue: 4 year: 2023 ident: 10.1016/j.eswa.2025.128809_b0085 article-title: ESG in China: A review of practice and research, and future research avenues publication-title: China Journal of Accounting Research – volume: 44 start-page: 1 issue: 2 year: 2021 ident: 10.1016/j.eswa.2025.128809_b0050 article-title: Fundamental ratios as predictors of ESG scores: A machine learning approach publication-title: Decisions in Economics and Finance doi: 10.1007/s10203-021-00364-5 – volume: 214 year: 2020 ident: 10.1016/j.eswa.2025.128809_b0110 article-title: An Xgboost based system for financial fraud detection publication-title: E3S Web of Conferences doi: 10.1051/e3sconf/202021402042 – volume: 44 start-page: 339 issue: 2 year: 2024 ident: 10.1016/j.eswa.2025.128809_b0010 article-title: Forecasting of S&P 500 ESG index by using CEEMDAN and LSTM approach publication-title: Journal of Forecasting doi: 10.1002/for.3201 – volume: 20 start-page: 184 year: 2023 ident: 10.1016/j.eswa.2025.128809_b0165 article-title: The impact of digital financial inclusion on corporate environmental performance publication-title: Statistics & Decision – volume: 6 issue: 9 year: 2023 ident: 10.1016/j.eswa.2025.128809_b0070 article-title: Analysis and comparison of loan default prediction models based on XGBoost and LightGBM algorithm publication-title: Academic Journal of Computing & Information Science – volume: 10 start-page: 4679 issue: 24 year: 2022 ident: 10.1016/j.eswa.2025.128809_b0135 article-title: Predicting fraud in financial payment services through optimized hyper-parameter-tuned XGBoost model publication-title: Mathematics doi: 10.3390/math10244679 – volume: 45 start-page: 1934 issue: 09 year: 2023 ident: 10.1016/j.eswa.2025.128809_b0125 article-title: Prediction and analysis model for ground peak acceleration based on XGBoost and SHAP.Chinese publication-title: Journal of Geotechnical Engineering – volume: 31 start-page: 3468 issue: 4 year: 2024 ident: 10.1016/j.eswa.2025.128809_b0065 article-title: China's ESG scorecard: A predictive machine learning model publication-title: Corporate Social Responsibility and Environmental Management doi: 10.1002/csr.2746 |
| SSID | ssj0017007 |
| Score | 2.4966626 |
| Snippet | The prediction of corporate ESG ratings is of paramount importance in augmenting the scientific rigor and precision of ESG investment decisions and steering... |
| SourceID | crossref elsevier |
| SourceType | Enrichment Source Index Database Publisher |
| StartPage | 128809 |
| SubjectTerms | ESG rating prediction Machine learning SHAP XGBoost algorithm |
| Title | Corporate ESG rating prediction based on XGBoost-SHAP interpretable machine learning model |
| URI | https://dx.doi.org/10.1016/j.eswa.2025.128809 |
| Volume | 295 |
| WOSCitedRecordID | wos001529393500003&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVESC databaseName: Elsevier SD Freedom Collection Journals 2021 issn: 0957-4174 databaseCode: AIEXJ dateStart: 19950101 customDbUrl: isFulltext: true dateEnd: 99991231 titleUrlDefault: https://www.sciencedirect.com omitProxy: false ssIdentifier: ssj0017007 providerName: Elsevier |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtZ3LTxQxGMAbBQ9eQHwERE0P3jZDdjuPtsfVrCAhhGTRbLhMti8DgVnCjrp_vt_Xx-wChqiJl8lkZtvZ9Ne0X78nIe_L0sJG4tCsXpmsmAq071Yiq-Qg14YJx7254OsRPz4Wk4k8idXs576cAG8asVjI6_-KGp4BbAyd_QvcXafwAO4BOlwBO1z_CHzKTWx7o_F-DwH7eHM0yHjWuG8ZtBFM9j_MZvM2Gx8MT3zaiOB8iKFUV97F0qaaEt9CwZxbWnxMkdzGRNApRG7FGH5PIX0I89DZuE-GF15Le2YXMfl31D2wu7qHLihm6YEUNIs8Kwah-E5aZFkopXlvwQ66g4s9O_-JWaBYuQcbpujL5fbUOQ2OsWPsF6Q2ECx4_pisM15KWI7Xh59Hk8POesT7IUw-_ZEYLBX8-u5-6fcCyYqQcfqMbMTTAR0GqlvkkW2ek81UeYPGhfgFOesgU4BMA2S6hEw9ZAo3q5DpLcg0QqYJMvWQX5Ivn0anHw-yWCUj0zkv2gzLi-XGKicdHJQqkVeqUqqaKqmkA_HdoMSKr6XNlTJ94Vh_qkrHLDMGTpP5K7LWzBq7TaizRheOa6NzW2hmFbOGCzNFP1QNcuEOGaShqnVMIY-VTC7r5Ct4UePw1ji8dRjeHdLr2lyHBCoP_rpMBOooAgbRroYJ80C71__Ybpc8Xc7rN2Stvflu35In-kd7Pr95F-fVLxeOgsI |
| linkProvider | Elsevier |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Corporate+ESG+rating+prediction+based+on+XGBoost-SHAP+interpretable+machine+learning+model&rft.jtitle=Expert+systems+with+applications&rft.au=Zhang%2C+Jianfeng&rft.au=Zhao%2C+Zexin&rft.date=2026-01-01&rft.pub=Elsevier+Ltd&rft.issn=0957-4174&rft.volume=295&rft_id=info:doi/10.1016%2Fj.eswa.2025.128809&rft.externalDocID=S0957417425024273 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0957-4174&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0957-4174&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0957-4174&client=summon |