EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Model parameter-based transfer learning for ESG score prediction in developing markets

Ivana Markovic, Adela Ljajic, Jelena Stankovic, Milos Kosprdic, Jovica Stankovic

Computer Science and Information Systems · 2026 · 23 (3) · 969-1000

DOI: 10.2298/csis250616028m ↗

Kurz gefasst

Fachartikel in der Zeitschrift Computer Science and Information Systems, 2026. Verfasst von Ivana Markovic und 4 weiteren Autor:innen. Die Arbeit nennt 24 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

While ESG (Environmental, Social, and Governance) assessment plays a key role in sustainable finance, data scarcity and noise in emerging economies hinder robust model development. To address this, we propose a model parameterbased transfer learning with random forest (MPBTL-RF) approach for domain adaptation situations where source data are not available. The proposed model is evaluated using three traditional learning approaches: Random Forest (RF), eXtreme Gradient Boosting (XGB), and Feedforward Neural Networks (FNN). Cross-validation is used to assess model generalizability, and domain adaptation is tested through indomain and out-of-domain settings. The proposed MPBTL-RF approach achieves competitive performance compared to traditional baselines in scenarios with limited training data, offering time advantages with predictive efficiency and stability. This work demonstrates how machine learning pipelines can adapt to data-constrained, real-world domains, fostering the synergy between AI (Artificial Intelligence) and business.

Zitieren

APA

Markovic, I., Ljajic, A., Stankovic, J., Kosprdic, M., & Stankovic, J. (2026). Model parameter-based transfer learning for ESG score prediction in developing markets. Computer Science and Information Systems, 23(3), 969-1000. https://doi.org/10.2298/csis250616028m

Vancouver

Markovic I, Ljajic A, Stankovic J, Kosprdic M, Stankovic J. Model parameter-based transfer learning for ESG score prediction in developing markets. Computer Science and Information Systems. 2026;23(3):969-1000. doi:10.2298/csis250616028m

BibTeX
@article{Markovic2026,
  author = {Markovic, Ivana and Ljajic, Adela and Stankovic, Jelena and Kosprdic, Milos and Stankovic, Jovica},
  title = {Model parameter-based transfer learning for ESG score prediction in developing markets},
  journal = {Computer Science and Information Systems},
  year = {2026},
  volume = {23},
  number = {3},
  pages = {969--1000},
  doi = {10.2298/csis250616028m}
}
Kostenlos starten →