A Multi-Scale Approach to Data-Driven Mass Migration Analysis Mohammed N. Ahmed 2 , Gianni Barlacchi 1,4 , Stefano Braghin 1 , Francesco Calabrese ⋆5 , Michele Ferretti 3 , Vincent Lonij 1 , Rahul Nair 1 , Rana Novack 2 , Jurij Paraszczak 5 , and Andeep S. Toor 2 1 IBM Research - Ireland 2 Global Business Services, IBM Corporation 3 King’s College London 4 University of Trento 5 New York University Abstract. A system for scenario analysis and forecasting of mass migra- tion is presented. The system consists of a family of multi-scale models to address the need of responding agencies for better situational aware- ness, short and medium-term forecasts of migration patterns, and assess impact of changes on the ground. Such insights allow for better planning and resource allocations to address migrant needs. The analytical frame- work consists of three separate models (a) a global push-pull model to es- timate macro-patterns, (b) a time-series prediction model for estimating future boundary conditions of crisis regions, and (c) a detailed network flow model that models population diffusion within the crisis region and allows for scenario modeling. The paper presents the framework using the European refugee crisis as a case study. In addition, overall system design, practical considerations, end-user applications, and limitations of the modeling approach are discussed. 1 Introduction 65.3 million people in the world today are forcibly displaced 6 . There are a further 232 million migrants worldwide who live outside their country of origin 7 . With these growing numbers, governments, international organizations, NGO’s and other stakeholders face an increasing challenge in responding to migration crisis, such as the one in Europe recently. If necessary data and tools were available to forecast displacement crisis, response actions can be better coordinated. In this paper, we present a data-driven approach to enable responders to manage mass migration events. Migration is an inherently complex and uncertain process. Direct observa- tions of migration patterns are typically partial and inaccurate. Paths and des- tinations for migration are influenced by a range of human factors. Information ⋆ Currently at Vodafone, Italy 6 http://www.unhcr.org/figures-at-a-glance.html 7 http://www.unfpa.org/migration