Key points are not available for this paper at this time.
Machine learning (ML) in the real estate industry has transformed property assessment, administration, and promotion, tackling significant issues including market instability and pricing precision. Notwithstanding considerable progress in predictive, descriptive, prescriptive analytics, and automation, current research mostly emphasises technological and operational efficiencies, overlooking the integration of environmental, social, economic, and governance (ESEG) sustainability dimensions. This monitoring constrains the advancement of comprehensive and accountable real estate solutions corresponding to sustainable development objectives. This study aims to address these gaps by systematically analyzing publication trends, key contributors, and thematic clusters, incorporating sustainability principles via a combination of bibliometric and content analysis approaches. The study uncovers publication trends, key research themes, and their alignment with ESEG criteria. The results highlight significant research clusters in predictive and descriptive analytics while revealing a notable deficiency in sustainability-focused studies. Implications of this study underscore the necessity for incorporating ESEG dimensions into ML-driven real estate practices, promoting resilient, equitable, and environmentally responsible industry advancements. This study provides actionable insights for stakeholders to enhance sustainable ML adoption, fostering long-term viability and societal well-being in the real estate sector.
Wang et al. (2026) studied this question.