Indonesian Journal of Multidisciplinary Science
Vol. 5 No. 1 (2025): Indonesian Journal of Multidisciplinary Science

A Systematic Review of Random Forest for Imbalanced Data Classification

Arief Ilham Syahputra (STMIK IKMI Cirebon)
Adinda Aulia Putri (STMIK IKMI Cirebon)



Article Info

Publish Date
26 Oct 2026

Abstract

Background: Class imbalance remains a fundamental challenge in supervised machine learning because minority classes often represent critical events such as fraud, disease, equipment failure, and severe traffic accidents. Although Random Forest is widely recognised for its robustness and predictive accuracy, its performance often deteriorates when learning from highly imbalanced datasets. Objective: This study examines Random Forest-based approaches to imbalanced classification, evaluates their effectiveness across application domains, and identifies emerging research trends and knowledge gaps. Method: This study employed a Systematic Literature Review (SLR) following PRISMA 2020 guidelines. A systematic search of the Scopus database identified 996 records, narrowed to 187 articles for eligibility assessment, of which 45 studies were included in the final synthesis. Results: The findings are organised into four themes: data-level imbalance handling, algorithm-level improvements, cross-domain performance evaluation, and emerging research trends. No single strategy consistently outperforms others across datasets and application domains. Classification performance depends on imbalance severity, data characteristics, minority-class representation, ensemble mechanisms, and application-specific requirements. Recent studies indicate increasing integration of generative oversampling, adaptive ensemble learning, and explainable artificial intelligence. Conclusion: This review proposes an integrated conceptual framework and taxonomy of Random Forest-based imbalance handling strategies, highlighting the importance of adaptive and interpretable approaches for trustworthy imbalanced classification systems.

Copyrights © 2025






Journal Info

Abbrev

ijoms

Publisher

Subject

Humanities Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Engineering Environmental Science Languange, Linguistic, Communication & Media Law, Crime, Criminology & Criminal Justice Library & Information Science Mathematics Public Health Social Sciences

Description

Indonesian Journal of Multidisciplinary Science (IJOMS) is a scientific journal in the form of research and can be accessed openly. This journal has e-ISSN 2808-6724 and p-ISSN 2808-5957. This journal is published monthly by International Journal Labs. The development of the company made the ...