Dipòsit Digital de Documents de la UAB
Publication
Artículo preliminar (WorkingPaper)
Forecasting bilateral refugee flows with high-dimensional data and machine learning techniques
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.
Project:
European Commission 882986
,
Agencia Estatal de Investigación CEX2019-000915-S
,
Agencia Estatal de Investigación PID2021-122605NB-I00
,
Agencia Estatal de Investigación RYC2021-033208-I
,
Agència de Gestió d'Ajuts Universitaris i de Recerca 2021/SGR-00571
View at: https://ddd.uab.cat/record/291789