This study presents a machine learning-based methodology to estimate the current state of food insecurity globally using secondary data on economic shocks, extreme weather events and conflicts. By predicting the prevalence of people with insufficient food consumption or at-crisis or above-crisis food-based coping levels when primary data are not available, the proposed model is a valuable tool for food aid efforts.
- Giulia Martini
- Alberto Bracci
- Elisa Omodei
