Enhancing global immunisation supply chains: integrating hybrid AI models into inventory optimisation considering non-monetary welfare metrics

We propose a Hybrid AI approach to forecast vaccine needs that combines domain-specific knowledge (though the UNICEF method) with probabilistic forecasts using Quantile Regression Averaging, which produce accurate probabilistic forecasts for the entire supply chain hierarchy. Forecasts then will be integrated into the inventory optimisation that accounts for non-monetary well-being metrics in the loss function, in addition to monetary costs.

The project will be empirically routed in and validated using available and forthcoming data of immunization programs from Kenya & Tanzania. The solution may then be adopted to other developing countries given similar immunization programs. The Hybrid AI approach that we intend to develop and employ fit under the "Artificial Intelligence and Robotics" cross-cutting theme.

The project also closely aligns with the "healthcare technologies" theme since it focuses on enhancing the efficiency of immunisation supply chains, which is critical for healthcare service delivery. The study contributes to the development of innovative solutions in the global healthcare sector by combining AI models with domain expert knowledge, and accounts for non-monetary wellbeing indicators.

The project leverages cutting-edge AI techniques for forecasting and optimisation in immunisation supply chains, and one of the outputs is improved forecasting and inventory control computational algorithms that can be embedded in the operations of immunisation supply chains via exciting ICT logistics systems. This aligns with the advancement of ICT in solving real-world challenges in the global healthcare supply

chain and distribution. The project builds on the research endeavours of the Data Lab for Social Good Research Group and the Forecasting for Social Good initiatives pioneered by Prof. Rostami-Tabar at Cardiff Business School.