Alternative Lens to Understand the Relationships Between Neighborhood Environment and Well-being with Capability Approach and Explainable Artificial Intelligence

The relationship between the neighborhood environment and well-being is attracting increasingly attention from researchers and policymakers, as the goal of development has shift from economy to well-being. However, existing literature predominantly adopts the utilitarian approach, understanding well-being as people’s feelings about their lives and viewing the neighborhood environment as resources that benefit well-being. The Capability Approach, a novel approach that conceptualize well-being as the freedoms to do or to be and regard environment as conversion factors that influence well-being, can offer new lens by incorporating human development into these topics. This paper proposes an alternative theoretical framework: well-being is conceptualized and measured by capability; neighborhood environment affects well-being by providing spatial services, functioning as environmental conversion factors, and serving as social conversion factors. We conducted a case study of Changshu City located in eastern China, utilizing multiple resource data, applying explainable artificial intelligence (XAI), namely eXtreme Gradient Boosting (XGBoost) and SHapley Additive exPlanations (SHAP). Our findings highlight the significance of viewing the neighborhood environment as a set of conversion factors, as it provides more explanatory power than providing spatial services. Compared to conventional research based on linear relationship assumption, our results demonstrate that the effects of neighborhood environment on well-being are non-linear, characterized by threshold effects and interaction effects. These insights are crucial for informing urban planning and public policy. This research enriches our understanding of well-being, neighborhood environment, and their relationship as well as provides empirical evidence for the core concept of conversion factors in the capability approach.