Housing acquisition decisions play a strategic role in shaping urban habitability and long-term sustainability, as they directly influence the quality of the built environment and users’ well-being. From an architectural and urban perspective, housing selection can be understood as an assessment of urban habitat quality, in which economic, spatial, social, environmental, and risk-related dimensions interact to define the conditions of livability. This study proposes a multi-objective decision-support framework that integrates evolutionary optimization algorithms (NSGA-II and MOEA/D) with multi-criteria decision analysis (TOPSIS) to support sustainable housing decisions. The model simultaneously considers four conflicting objectives: minimizing acquisition cost, minimizing spatial accessibility and disutility from essential services, maximizing socio-spatial safety and long-term habitat value, and minimizing environmental and territorial risk. A real-world case study in the Tampico metropolitan area demonstrates how the proposed approach generates Pareto-optimal housing alternatives that explicitly reveal trade-offs between habitability dimensions. The resulting non-dominated solutions are subsequently ranked using TOPSIS to reflect user-centered preferences and facilitate transparent decision-making. The results show that the proposed framework effectively operationalizes the concept of urban habitat quality through an explainable, customizable computational tool, thereby contributing to sustainable urban development, resilience, and informed housing choices. This research supports the technological enablement of habitat assessment and aligns with the objectives of SDG 11: Sustainable Cities and Communities, offering a replicable methodology for urban and architectural decision-making contexts.
García-Morales et al. (Thu,) studied this question.