PENULIS
TANGGAL
ABSTRAK
Early detection of sustainability risks has become increasingly critical for non-profit organizations and public institutions, which must maintain accountability, transparency, and long-term resilience amid growing environmental, social, and governance (ESG) challenges. This study investigates the role of machine learning in supporting early warning systems for sustainability risk identification within these organizations. Using supervised and unsupervised learning techniques, the research analyzes key indicators related to operational performance, financial stability, stakeholder engagement, and environmental impact. The study develops a predictive risk model and evaluates its accuracy, interpretability, and applicability within the context of public and non-profit governance. Results show that machine learning improves the timeliness and precision of risk detection, enabling organizations to anticipate vulnerabilities, enhance decision-making processes, and strengthen sustainability strategies. This research contributes to the literature by presenting an analytical framework that integrates machine learning with sustainability risk management, offering practical implications for policymakers, organizational leaders, and practitioners seeking to enhance institutional resilience and long-term sustainability.