Analyzing Social Enterprise Case Studies and Their Metrics/Challenges Using Graph Neural Networks

Abstract

Social enterprises are unique organizations that help in solving social problems including poverty, women and children oppression, and environmental conservation. Yet, these organizations are confronted with constraints such as funding, policy disadvantages and some other limitations that pose a threat to the sustainability of the project. This research uses Graph Neural Networks to verify how entities interact in the context of social enterprises, the performance indicators, and the issues that they experience. To build up the directed graph showing details about the four highlighted social enterprises–Grameen Bank, BRAC, SEWA and Eco-Enterprises along with their goals and challenges, such as poverty reduction, scalability, sustainability and funding constraints, and policy gaps, each of the four has been highlighted as below: The GNN analysis in this study provides a clear understanding of interaction between them, as important challenge like funding and policy gaps becomes clear as the factors hindering success. The paper also discusses the ability of GNNs to capture various types of relations and provides recommendations for social ventures, government, and financiers. The implications highlight the role of general, sustainable development objectives to address the issues of scalability and in relation to the policy dimensions. The study contributes to the existing literature on methods of computational social sciences and presents a novel approach leveraging GNNs for social enterprise analysis and presents the applicability of GNNs in enhancing decision making and strategic planning for social enterprises.