View article

Humanitarian predictive analytics is the use of big data to feed machine learning and statistical models to calculate the probable characteristics of humanitarian emergencies. The technology is being used to forecast the likely trajectory and features of humanitarian emergencies including pandemics, famines, natural disasters and refugee movements. This form of artificial intelligence is used to predict where and when disasters will unfold, what the defining characteristics of the situation will be and who will be the most affected populations. Accurate advance prediction enables the pre-positioning of emergency relief finance, supplies and personnel.

Forecasting and early warning systems have always been a component of humanitarian action. However, the rapid expansion of computing power and big data has dramatically increased the potential for predictive analytics in evermore areas of humanitarian action. In the last few years, the term predictive analytics has come to refer primarily to a digital process, drawing on multiple sources of electronic data feeding machine learning algorithms to inform statistical models that compute the probability of different humanitarian outcomes. Historic data of previous humanitarian events plus mobile phone records and social media posts can provide the high volumes of data needed to analyse food security, predict malnutrition and inform aid deployment. Satellite images, meteorological data and financial transactions can be used to track and predict the escalation and trajectory of refugee movements.