Our solution centers on the dynamic interactions between people and urban environments, analyzing how these connections enhance well-being. To accurately model well-being in urban settings, we require a framework that
captures the complexity of both environmental and psychological factors without oversimplification. To achieve this, we employ a multi-stage nested Bayesian network, inspired by convolutional neural networks, to simulate and
interlink these intricate interactions. This approach, named Convolutional Socio-Ecological Well-being Network, ensures a balance between complexity and predictive accuracy, enabling us to model well-being outcomes effectively.
