In today's era of rapid urbanization, smart cities are emerging as a beacon of efficiency and sustainability. At the heart of this evolution is the integration of Machine Learning (ML), which can transform vast streams of data into informed decisions. This article examines through a literature review the transformative potential of machine learning in urban environments, highlighting advances and challenges in the key smart city domains: Infrastructure, Environment, Mobility and Transport. The review highlights both the promising breakthroughs achieved and the challenges ahead in this interdisciplinary field. Our analysis aims to provide readers with a comprehensive understanding of how machine learning not only improves data processing capabilities, but also leads to actionable and impactful decisions in the urban context. By tracing the path from raw data to informed urban solutions, this paper highlights the central role of machine learning in shaping the smart cities of the future.