Advances in computational urbanism have stimulated the rise of generative and parametric approaches to urban design. Yet, most generative and parametric approaches focus on physical characteristics, such as a neighborhoods walkability, energy efficiency, and urban form. Here, we study the colocation patterns of more than one million amenities in 47 U.S. cities to model the amenity mix of neighborhoods, and to identify the amenities that are over- or under-supplied in a neighborhood. We build this model by combining a clustering algorithm, designed to identify amenity-dense neighborhoods, and a network, connecting amenities that are likely to collocate. Our findings extend generative and parametric urban design approaches to the amenity mix of neighborhoods, by leveraging the idea of relatedness from the economic geography literature, to evaluate and optimize a neighborhood's amenity mix.

计算城市化的进步刺激了生成和参数化城市设计方法的兴起。但是，大多数生成和参数化方法都将重点放在物理特征上，例如街区的步行性，能效和城市形态。在这里，我们研究了美国47个城市中超过一百万个便利设施的共置模式，以模拟社区的便利性组合，并确定社区中供过于求的设施。我们通过将旨在识别舒适性密集社区的聚类算法和连接可能搭配的便利设施的网络相结合来构建此模型。我们的发现通过利用经济地理文献中的相关性概念，将生成性和参数化城市设计方法扩展到社区的舒适性组合中，