Bayesian Projection of Extant Refugee and Asylum Seeker Populations

TL;DR

This paper introduces a Bayesian hierarchical time-series model to forecast refugee and asylum seeker populations, effectively capturing growth and decline phases and providing accurate long-term projections for multiple countries.

Contribution

It presents a novel Bayesian modeling pipeline that explicitly models refugee population dynamics with growth and decline phases, improving forecast accuracy.

Findings

Model performs well at 1, 5, and 10-year horizons.

Accurate projections for 35 countries of origin.

Effective in capturing population growth and decline phases.

Abstract

Estimates of future migration patterns are of broad interest in demography. Forced migration, including refugee and asylum seekers, plays an important role in overall migration patterns, but is notoriously difficult to forecast. Focusing on refugees and asylum seekers, we propose a modeling pipeline based on Bayesian hierarchical time-series modeling for projecting refugee population official statistics by country of origin using data from the United Nations High Commissioner for Refugees (UNHCR). Our approach is based on a conceptual model of refugee and asylum seeker populations following growth and decline phases, separated by a peak. The growth and decline phases are modeled by logistic growth and decline through an interrupted logistic process model. We evaluate our method through a set of validation exercises that show it has good performance for forecasts at 1, 5, and 10 year horizons, and we present projections for 35 countries of origin of large refugee and asylum seeker population.