A newer version of this project is available. See below for other available versions.

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

Principal Investigator(s):  View help for Principal Investigator(s) Konstantin Boss, UAB & BSE; Andre Groeger, UAB, BSE, MOVE; Tobias Heidland, Kiel Institute for the World Economy & Kiel University; Conghan Zheng, UAB & BSE; Finja Krueger, Kiel Institute for the World Economy (IfW), Kiel University, and Institute for the Study of Labor (IZA)

Version:  View help for Version V2

Name File Type Size Last Modified
  CODE 08/05/2024 10:58:AM
  DATA 05/28/2024 09:37:AM
  OUTPUT 05/28/2024 09:12:AM
GTI_codebook.csv text/csv 32.5 KB 05/28/2024 05:25:AM
README.txt text/plain 2.3 KB 08/05/2024 07:00:AM
toc_monthly.csv text/csv 264.2 KB 05/28/2024 04:51:AM

Project Citation: 

Boss, Konstantin, Groeger, Andre , Heidland, Tobias, Zheng, Conghan , and Krueger, Finja . Forecasting Bilateral Refugee Flows with High-dimensional Data and Machine Learning Techniques*. Ann Arbor, MI: Inter-university Consortium for Political and Social Research [distributor], 2024-08-05. https://doi.org/10.3886/E198322V2

Project Description

Summary:  View help for Summary
We develop monthly refugee flow forecasting models for 157 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.

Scope of Project

Subject Terms:  View help for Subject Terms migration; forecasting; machine learning; google trends


Related Publications

Download this project

Published Versions

V3 [2024-08-05]

V2 [2024-08-05]

V1 [2024-05-28]

Export Metadata

Dublin Core

DDI 2.5

Report a Problem

Found a serious problem with the data, such as disclosure risk or copyrighted content? Let us know.

This material is distributed exactly as it arrived from the data depositor. ICPSR has not checked or processed this material. Users should consult the investigator(s) if further information is desired.