Enhancing Humanitarian Supply Chain Resilience: Evaluating Artificial Intelligence and Big Data Analytics in Two Nations

Abstract

Background: This study examines the application of Artificial Intelligence (AI) and Big Data Analytics (BDA) in enhancing humanitarian supply chain resilience, focusing on Ghana and South Africa. Despite their potential, AI-BDA applications are underexplored in disaster response, particularly in developing economies. Methods: An explanatory research design using a quantitative approach was employed, analyzing data from 200 supply chain professionals in both nations. Structured questionnaires assessed the implementation of four key AI-BDA techniques: Time-Series Forecasting (TSF), Early Warning Systems (EWS), Logistics Optimization (LO), and Real-time Monitoring (RTM). Exploratory factor analysis and regression analysis were conducted to evaluate the relationship between these techniques and supply chain resilience, controlling for organizational size and technological readiness. Results: The findings indicate that AI-BDA techniques significantly improve humanitarian supply chain resilience, with TSF and LO demonstrating the highest predictive power. Additionally, technological readiness facilitates the adoption of these techniques. Conclusions: While AI-BDA offers substantial benefits, opportunities for greater adoption remain, particularly in real-time monitoring and predictive analytics. Humanitarian organizations should invest in capacity-building initiatives, enhance data quality, and foster multi-stakeholder partnerships to maximize the impact of AI-BDA.