• Agent Based Models
• Schelling Model
• Simulations
• Social AI

Schelling’s model is the most known ABMs for urban segregation, showing how collective dynamics comes from individual preferences. Many variants and improvements of the Schelling model have been proposed, changing aspects regarding the agents’ behavior, the environment’s configuration, or considering information about geographical regions to capture real-world aspects of an urban environment. In this thesis, I developed a python library for segregation models and comparing the outcomes of several of them. In particular, I designed different mobility-driven segregation models that introduce in the agent’s destination evaluation cell score linked to its attractiveness, associated with the offer of services of that particular location. I also introduced the possibility of extracting traces of mobility of individual agents to observe how these change according to the variation of models parameters.