Introduction to Urban Analytics (Spring 2023)

Introduction. This course introduces the primary modeling paradigms to analyze cities with an emphasis on analytical perspectives and urban applications. The course consists of four study modules with the first three introducing regression, network science, and machine learning and the module four discussing their integration. The regression module introduces linear and logistic regression from the statistics tradition, applied to the analysis of urban economy and mobility. The network module introduces the spatial networks, spatial regression, power-law scaling, and urban network dynamics. The machine learning module introduces supervised and unsupervised learning, and deep learning with applications to mobility networks and urban imagery. The course discusses the similarities and differences of the three analytical paradigms and introduces how to integrate them in the fourth study module. The course will also provide broad urban analytical perspectives by touching upon optimization, causal inference, generative models, and social justice in cities. Students will learn Python packages, such as Pandas, GeoPandas, and Scikit-learn to analyze urban mobility, economic development, resilience, and housing. This course focuses on intuition and application of the analytical tools to urban topics, rather than theory or math foundations. It provides future urban planners, designers, and engineers the critical analytical capacity to understand cities and address upcoming urban challenges.