DREAM-KG is an open knowledge network designed to partially address homelessness by integrating social, economic, environmental, and political factors into a structured and interpretable knowledge graph.

This project aims to create a knowledge graph, DREAM-KG, that provides a comprehensive understanding of the social, economic, and political factors that contribute to homelessness, while organizing existing services and resources to support people experiencing homelessness.

The primary users of the system include people experiencing homelessness, front-line case workers, law enforcement agents, non-profit organizations, and federal agencies. DREAM-KG will help users understand structural factors, effective intervention methods, community resources, cultural nuances, and policy knowledge from local to federal levels.

The project uses topological data analysis, artificial intelligence models, and ontology techniques for data acquisition, integration, and analysis. By combining geometric theory, explainable AI, and semantic technologies, the project aims to advance AI applications, bridge AI and homelessness research, and offer novel solutions for homelessness prevention.