AI-enabled Urban land valuation and smart real estate planning for sustainable cities

This review examines how Artificial Intelligence (AI) is being applied to urban land valuation, spatial planning and housing market analysis, and under what conditions it can support sustainable and equitable urban development. It combines a PRISMA-guided systematic literature review of 87 studies published between 2015 and 2025 with a documentary comparison of three purposively selected national contexts: India, Singapore and Canada. The evidence indicates that machine-learning-based Automated Valuation Models (AVMs) frequently improve predictive accuracy over conventional hedonic regression where rich geospatial data are available. However, only a minority of the reviewed studies apply AI, and empirical evidence that AI-based valuation improves transparency, reduces inequality or advances sustainability in statutory practice remains limited. Experience from mature AVM markets in the United States, the European Union, the United Kingdom and China shows that model performance is bounded by the quality and representativeness of training data, and that assessment regressivity, appraisal bias and model risk persist unless they are explicitly governed. The country comparison is presented as an interpretive typology of institutional readiness rather than a measured ranking. The review proposes a conceptual framework linking AI-enabled valuation to Sustainable Development Goal 11 (Sustainable Cities and Communities), in which data governance, training-data auditing, explainability and human oversight are treated as preconditions for, rather than by-products of, the potential benefits of AI.