Forecasting Internally Displaced People’s Movements with Artificial Intelligence

The rise of big data and artificial intelligence (AI) has paved the way for data-driven interventions in the field of international development. In this paper, a group of researchers (i) summarizes policies and implications of the use of advanced technology in the field and (ii) presents the result of the study they conducted which applies machine learning to forecast internally displaced people’s (IDPs) movements in the Democratic Republic of the Congo. Despite methodological limitations, the results confer an exposition on how machine learning models and open-source data could enhance the predictive insights of forced displacement. Our approach could be used to predict not only IDP flows but also refugee flows, expanding the use of machine learning for social good. To counter future crises triggered by climate change and the COVID-19 pandemic, we believe our approach has a great possibility to support the effective distribution of limited funds and supplies. This study underscores the benefit of AI and highlights issues in implementations. Future research will need to widen target regions and periods as well as to include the pragmatic aspects of the implementations.