Forecasting Bilateral Refugee Flows with High-dimensional Data and Machine Learning Techniques

  • Authors: Andre Groeger.
  • BSE Working Paper: 1387 | March 23
  • Keywords: learning , forecasting , European Union , refugee flows , asylum seekers , machine , Google trends
  • JEL codes: C53, C55, F22
  • learning
  • forecasting
  • European Union
  • refugee flows
  • asylum seekers
  • machine
  • Google trends
Download PDF Download pdf Icon

Abstract

We develop monthly refugee flow forecasting models for 150 origin countries to the EU27, using machine learning and high-dimensional data, including digital trace data from Google Trends. Comparing different models and forecasting horizons and validating them out-of-sample, we find that an ensemble forecast combining Random Forest and Extreme Gradient Boosting algorithms consistently outperforms for forecast horizons between 3 to 12 months. For large refugee flow corridors, this holds in a parsimonious model exclusively based on Google Trends variables, which has the advantage of close-to-real-time availability. We provide practical recommendations about how our approach can enable ahead-of-period refugee forecasting applications.

Subscribe to our newsletter
Want to receive the latest news and updates from the BSE? Share your details below.
Founding institutions
Distinctions
Logo BSE
© Barcelona Graduate School of
Economics. All rights reserved.
YoutubeFacebookLinkedinInstagramX