Abstract

This study aims to analyze the characteristics and driving forces of AI-driven micro-housing; evaluate its implications for future urban development through computational modeling, and propose algorithmic frameworks for integrating micro-housing into sustainable urban development (SDG 11). A hybrid research design was employed, combining qualitative documentary analysis with quantitative computational frameworks. The STEEP framework was augmented with AI-driven trend forecasting to examine drivers influencing Micro Living. The study utilizes Genetic Algorithms (GA) to simulate spatial optimization in compact units and Reinforcement Learning (RL) models to evaluate energy efficiency in smart infrastructure. The findings indicate that Micro Living is a structural adaptation supported by predictive AI systems and real-time data analytics. Micro Living is not merely a housing trend but a structural adaptation to urban density, digital lifestyles, and changing household patterns. It supports compact city development, efficient resource use, and the integration of smart infrastructure. The study concludes that Micro Living should be developed within an integrated planning framework that balances spatial efficiency, quality of life, and sustainability. The findings contribute to urban studies by positioning Micro Living as a multidimensional component of future urban transformation.