To what extent can spreadsheets shape sustainability? A machine learning approach to ESG score prediction

Stránka jednoduchej položky
dc.contributor.authorMusa, Hussam
dc.contributor.authorMusová, Zdenka
dc.contributor.authorRech, Frederik
dc.contributor.authorGrofčíková, Janka
dc.date.accessioned2026-09-08T07:23:19Z
dc.date.available2026-09-08T07:23:19Z
dc.date.issued2026
dc.descriptionIn: Transformations in Business & Economics. Kaunas : Vilnius University, 2026. ISSN 1648-4460. Vol. 25, no. 2 (68) (2026), pp. 235-260.
dc.description.abstractThis study examines whether corporate ESG ratings can be predicted using multi-year lagged financial indicators. The objective is to evaluate the extent to which historical financial information explains ESG performance among Slovak manufacturing firms. The analysis uses a sample of 974 Slovak manufacturing firms with ESG ratings for 2023 and financial data from 2018–2022. The primary model applies XGBoost with recursive feature elimination and SHAP analysis, while a PCA-based one-vs-rest XGBoost model is used as a robustness check. The findings show that historical financial indicators provide meaningful but incomplete information about ESG performance. Leverage, liquidity, debt-servicing capacity, firm age, and tax-related indicators emerge as important predictors. Older lagged variables also remain significant, suggesting that ESG outcomes reflect longer-term financial patterns. The alternative model improves prediction, particularly for the Environmental and Governance pillars, whereas the aggregate ESG score remains more difficult to classify. The models predict the middle ESG rating category most reliably, while performance for extreme categories is limited by class imbalance and the ordinal structure of ESG scores. The study concludes that financial data can support ESG prediction, especially at the pillar level, but cannot replace qualitative and ESG-specific information.
dc.description.sponsorshipVEGA 1/0479/23 Výskum cirkulárneho spotrebiteľského správania v kontexte STP marketingového modelu VEGA 1/0120/25 Výskum paradigiem a determinantov procesov riadenia a implementácie ESG v kontexte požadovanej finančnej výkonnosti podnikov a zmien vyplývajúcich z CSRD smernice APVV-23-0018 Zelené verejné obstarávanie ako nástroj inovatívnych environmentálnych riešení
dc.identifier.doihttps://doi.org/10.15388/Tibe.2026.25.2.21
dc.identifier.issn1648-4460
dc.identifier.issn2538-872X
dc.identifier.urihttps://repo.umb.sk/handle/123456789/1620
dc.language.isoen
dc.publisherVilnius University : Kaunas
dc.rightsCC BY Creative Commons Attribution 4.0 International
dc.rightsinfo:eu-repo/semantics/openAccess
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectenvironmentálne
dc.subjectsociálne a riadiace faktory
dc.subjectESG faktory
dc.subjectESG factors
dc.subjectenvironmental
dc.subjectsocial
dc.subjectand governance factors
dc.subjectfinancial indicators
dc.subjectfinančné ukazovatele
dc.subjectkey financial indicators
dc.subjectstrojové učenie
dc.subjectmachine learning
dc.subjectvýrobné spoločnosti
dc.subjectmanufacturing companies
dc.subjectpodnikanie na Slovensku
dc.subjectbusiness in Slovakia
dc.titleTo what extent can spreadsheets shape sustainability? A machine learning approach to ESG score prediction
dc.typeArticle
dc.typeinfo:eu-repo/semantics/article

Na stiahnutie

Pôvodný balík
Teraz sa zobrazuje 1 - 1 z 1
Obrázok miniatúry
Veľkosť:
941.86 KB
Formát:
Adobe Portable Document Format
Stiahnuť

Kolekcie

08 Články v časopisoch