About the journal

• Home page
• Contact information
• Aims and scope
• Indexing information
• Editorial policies
• ComSIS consortium
• Journal boards
• Managing board

For authors

• Information for contributors
• Article submission
• Accepted papers
• Copyright transfer form
• Download section

For readers

• Forthcoming articles
• Current issue
• Archive

For reviewers

• Review submissions
• Review submissions OJS

News

• Journal's Facebook page
• Special issue proposal
• Calls for special issues

Model Parameter-Based Transfer Learning for ESG Score Prediction in Developing Markets

Ivana Marković¹   , Adela Ljajić²   , Jelena Z. Stanković¹   , Miloš Košprdić²   , Jovica Stanković¹   

1. Faculty of Economics, University of Niš Trg kralja Aleksandra Ujedinitelja 11, 18000 Niš
   ivana.markovic@eknfak.ni.ac.rs (corresponding author), jelenas@eknfak.ni.ac.rs, jovica.stankovic@eknfak.ni.ac.rs
2. The Institute for Artificial Intelligence Research and Development of Serbia Fruškogorska 1, 21000 Novi Sad
   adela.ljajic@ivi.ac.rs, milos.kosprdic@ivi.ac.rs

Abstract

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 parameter based transfer learning with random forest (MPBTL-RF)approachfordomainadap tation situations where source data are not available. The proposed model is evalu ated using three traditional learning approaches: Random Forest (RF), eXtreme Gra dient Boosting (XGB), and Feedforward Neural Networks (FNN). Cross-validation is used to assess model generalizability, and domain adaptation is tested through in domain 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.

Key words

Machine Learning, Domain Adaptation, Transfer Learning, Small Datasets, ESG Score, Developing Markets, Corporate Financial Performance.

Digital Object Identifier (DOI)

https://doi.org/10.2298/CSIS250616028M

Publication information

Volume 23, Issue 3 (June 2026)
Year of Publication: 2026
ISSN: 2406-1018 (Online)
Publisher: ComSIS Consortium

Full text

Available in PDF
Portable Document Format

How to cite

Marković, I., Ljajić, A., Stanković, J.Z., Košprdić, M., Stanković, J.: Model Parameter-Based Transfer Learning for ESG Score Prediction in Developing Markets. Computer Science and Information Systems, 23(3), 969–1000 (2026). https://doi.org/10.2298/CSIS250616028M