Agent-based Modeling meets the Capability Approach for Human Development: Simulating Homelessness Policy-making

2025-03-24

AI Summary

This paper addresses global homelessness by proposing a policy evaluation framework integrating the Capability Approach (CA) with computational modeling. Methodologically, it formalizes CA as a values-driven Markov Decision Process (MDP), embedded within multi-agent modeling and reinforcement learning, and constructs behavior models through stakeholder-engaged co-design. Contributions include: (1) enabling computationally tractable and interpretable policy simulation grounded in CA; (2) supporting non-intrusive assessment of capability restoration pathways for housing-insecure populations; and (3) demonstrating cross-contextual applicability through validation on real-world health inequity and homelessness cases. The framework provides an ethically grounded, data-enhanced simulation tool for SDG-aligned, inclusive, and iterative social policy design and evaluation. (136 words)

Technology Category

• Humans and AI: Learning Human Values and Preferences
• Application Domains: Humanities & Computational Social Science
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior

Application Category

• User Modeling, Personalization and Recommendation: Accountability, Transparency, and Ethics for personalization
• Economics, Online Markets and Human Computation: Fairness, privacy, and diversity in economic environments
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

The global rise in homelessness calls for urgent and alternative policy solutions. Non-profits and governmental organizations alert about the many challenges faced by people experiencing homelessness (PEH), which include not only the lack of shelter but also the lack of opportunities for personal development. In this context, the capability approach (CA), which underpins the United Nations Sustainable Development Goals (SDGs), provides a comprehensive framework to assess inequity in terms of real opportunities. This paper explores how the CA can be combined with agent-based modelling and reinforcement learning. The goals are: (1) implementing the CA as a Markov Decision Process (MDP), (2) building on such MDP to develop a rich decision-making model that accounts for more complex motivators of behaviour, such as values and needs, and (3) developing an agent-based simulation framework that allows to assess alternative policies aiming to expand or restore people's capabilities. The framework is developed in a real case study of health inequity and homelessness, working in collaboration with stakeholders, non-profits and domain experts. The ultimate goal of the project is to develop a novel agent-based simulation framework, rooted in the CA, which can be replicated in a diversity of social contexts to assess policies in a non-invasive way.

Problem

• Combining capability approach with agent-based modeling for homelessness solutions
• Developing MDP-based framework to assess policies for human development
• Simulating health inequity and homelessness with stakeholder collaboration

Innovation

• Combines capability approach with agent-based modeling
• Implements CA as Markov Decision Process (MDP)
• Develops simulation framework for policy assessment