InclusiViz: Visual Analytics of Human Mobility Data for Understanding and Mitigating Urban Segregation

Urban segregation extends beyond where people live to where they work and socialize: The research reveals that previous studies focused primarily on residential segregation, but InclusiViz demonstrates the importance of analyzing "activity spaces"—locations where people work, socialize, and engage in leisure—to capture a more complete picture of urban inequality and social division.

Machine learning can identify environmental features that drive segregation patterns: The system uses a deep learning model to predict how different social groups move through cities based on environmental features, and employs explainable AI to reveal which specific features influence segregation, making the model's decision-making transparent rather than a "black box."

Visual analytics tools can empower urban planners to test interventions in real-time: InclusiViz allows users to evaluate how proposed urban planning changes might affect segregation patterns with immediate feedback, enabling data-driven decision-making rather than relying on intuition or incomplete information.

Expert validation confirms practical value for addressing real-world inequality: Case studies and interviews with social scientists and urban analysts demonstrated the system's effectiveness, suggesting that this type of responsible AI application can meaningfully guide cities toward more inclusive urban planning and help mitigate socioeconomic and racial tensions.