A Genetic Algorithm-Based Decision Support Framework for Context-Sensitive Mass-Housing Design: A Case Study of Zeytinburnu, Istanbul

In the modern era, mass-housing production has generally prioritized efficiency and standardization at the expense of architectural diversity and contextual sensitivity. This study proposes a computational decision-support model for the early design phase of mass housing that responds to site-specific conditions while maintaining the efficiency of industrialized housing production through the integration of parametric modeling and genetic algorithms. Using the Zeytinburnu-Kazlıçeşme district of Istanbul as a case study, a parametric model integrating the multi-objective genetic algorithm engine Wallacei X was developed in Rhino–Grasshopper. The model is structured around fundamental design variables, contextual rules, and planning constraints to generate feasible and diverse massing configurations. Four fitness objectives were evaluated simultaneously: total construction area, building footprint area, open (garden) area, and total terrace area. In a single exploratory run, 200 massing alternatives were generated, from which 32 solutions satisfying the adopted FAR/BCR screening criteria, 26 Pareto-optimal solutions, and five selected alternatives at the intersection of both sets were identified. These solutions were evaluated through a decision-support workflow based on objective performance, Pareto optimization, and the adopted local density-screening criteria. The findings indicate that genetic algorithm-based generative design can support architectural diversity, contextual sensitivity, and informed decision-making in residential housing design.