haracterizing the socio-economic status of populations and providing reliable and up-to-date estimates of who the most vulnerable are, how many they are, where they live and why they are vulnerable is essential for governments and humanitarian organizations to make informed and timely decisions on implementation of humanitarian assistance policies and programmes 1 . These data are traditionally collected through face-to-face surveys. However, these are expensive, time-consuming and, in certain areas, not possible to perform due to conflict, disease, insecurity or remoteness. Therefore, during the past few years, researchers have begun to investigate the potential of non-traditional data and new computational methods to estimate vulnerabilities and socio-economic characteristics when primary data are not available. In these studies, mobile phone data 2 , satellite imagery 3 , a combination of both 4,5 , mobile money transaction records 6 , geolocated Wikipedia articles 7 or tweets 8 and social media advertising data 9 have been used in combination with state-of-the-art machine learning methods to provide reliable estimates of poverty at different spatial resolutions for several sub-Saharan African countries and southern and southeastern Asian ones.

Lack of regular physical or economic access to safe, nutritious and sufficient food is a critical issue affecting millions of people world-wide. Estimating how many and where these people are is of fundamental importance for governments and humanitarian organizations to take informed and timely decisions on relevant policies and programmes. In this study, we propose a machine learning approach to predict the prevalence of people with insufficient food consumption and of people using crisis or above crisis food-based coping when primary data is not available. Making use of a unique global data set, we show that the proposed models can explain up to 78% of the variation in insufficient food consumption and crisis or above food-based coping levels. We also show that the proposed models can be used to nowcast the food security situation in near-real time and propose a method to identify which variables are driving the changes observed in predicted trends, which is key to make predictions serviceable to decision makers.