[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-124828-en":3,"doc-seo-124828-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},124828,4398048949847,"Eliana","https://ap-avatar.wpscdn.com/avatar/400002536579ef2da7f?_k=1778318612642679267",8,"Research & Report","Forecasting Bilateral Refugee Flows with High-dimensional Data and Machine Learning Techniques - Research Report","Develops monthly refugee flow forecasting models for 150 origin countries to the EU27 using machine learning with high-dimensional inputs, including digital trace data from Google Trends. Evaluations across models and forecast horizons with out-of-sample validation show that an ensemble combining Random Forest and Extreme Gradient Boosting delivers consistent gains for 3–12 month horizons. For major refugee-flow corridors, a compact model based only on Google Trends variables achieves comparable performance while enabling near real-time, ahead-of-period forecasting applications. Provides practical implementation guidance.","Forecasting Bilateral Refugee Flows with High-dimensional Data and Machine Learning Techniques  \nBSE Working Paper 1387 | March 2023  \nKonstantin Boss, Andre Groeger, Tobias Heidland, Finja Krueger, Conghan Zheng  \nForecasting Bilateral Refugee Flows with High-dimensional Data and Machine Learning  \nTechniques ∗  \nKonstantin Boss Andre Groeger Tobias Heidland  \nFinja Krueger Conghan Zheng  \nMarch 2, 2023  \nAbstract  \nWe 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.  \nKeywords: Forecasting, refugee flows, asylum seekers, European Union, machine learning, Google Trends  \nJEL codes: C53, C55, F22  \n∗ Boss: Universitat Autonoma de Barcelona (UAB), Barcelona School of Economics (BSE), kon[stantin.boss@bse.eu](stantin.boss@bse.eu) ; Groeger: Universitat Autonoma de Barcelona (UAB), Barcelona School of Economics (BSE) and Markets, Organizations and Votes in Economics (MOVE), [andre.groger@uab.es](andre.groger@uab.es) ; Heidland: Kiel Institute for the World Economy (IfW), Kiel University, [tobias.heidland@ifw-kiel.de](tobias.heidland@ifw-kiel.de) ; Krueger: Kiel Institute for the World Economy (IfW), Kiel University, and Institute for the Study of Labor (IZA), [finja.krueger@ifw-kiel.de](finja.krueger@ifw-kiel.de) ; Zheng: Universitat Autonoma de Barcelona (UAB), Barcelona School of Economics (BSE), [conghan.zheng@uab.cat](conghan.zheng@uab.cat).  \nAcknowledgements: We thank Joop Adema, Joshua Blumenstock, Stefano M. Iacus, Hannes Mueller, Jasper Tjaden, Ingmar Weber, Emilio Zagheni and conference and seminar participants at the 12th CEPII-LISER-OECD Annual Conference on “Immigration in OECD Countries” 2022 (Paris), Workshop on New Data and New Methods for Migration Studies 2022 (Paris), Forecasting for the Social Good Workshop 2022 of the International Symposium of Forecasters (Oxford), Bertelsmann Foundation Migration Prediction Workshop 2022 (Berlin), and the Workshop on Computational Conflict Research 2022 at Ludwig-Maximilian University (Munich) for very useful comments. We acknowledge financial support from the European Commission’s Horizon 2020 program through the project “IT Tools and Methods for Managing Migration Flows”(ITFLOWS; grant number: 882986) . Boss, Groeger, and Zheng acknowledge financial support from the Spanish Agencia Estatal de Investigaci´on (AEI) through the Severo Ochoa Programme for Centres of Excellence in R&D (Barcelona School of Economics CEX2019- 000915-S) . Boss also acknowledges support through grant FPI PRE2020-093941 . Groeger also acknowledges financial support through grant PID2021-122605NB-I00 funded by MCIN/AEI/10.13039/501100011033 and by ERDF A way of making Europe, through MCIN/RYC2021-033208-I/AEI/10.13039/501100011033 and the European Union “NextGenerationEU”/PRTR, as well as from the Generalitat de Catalunya (2021-SGR-00571) . The usual disclaimer applies.  \n1 Introduction  \nIn 2013-2015, the European Union experienced a substantial increase in refugee flows, with more than 1 .2 million asylum applications registered at its peak in 2015 alone.1 The experience of 2015 has triggered widespread political debate and stressed the importance of preparedness for governments and humanitarian organizations to ensure safe conditions for asylum seekers and refugees en route and upon arrival. That increased political atte","cbCaibf1cLIsIrfm","https://ap.wps.com/l/cbCaibf1cLIsIrfm","pdf",629495,1,49,"English","en",105,"# Abstract\n## Methodology and data sources\n## Model comparison and forecast horizons\n## Findings for large corridors\n## Practical recommendations","[{\"question\":\"What data and modeling approach are used to forecast refugee flows?\",\"answer\":\"The study builds monthly forecasting models for 150 origin countries to the EU27 using machine learning and high-dimensional data, including digital trace data from Google Trends.\"},{\"question\":\"Which ensemble method performs best and for what horizon range?\",\"answer\":\"An ensemble forecast combining Random Forest and Extreme Gradient Boosting consistently outperforms other models for forecast horizons between 3 and 12 months.\"},{\"question\":\"How can forecasting be done in near real time for large corridors?\",\"answer\":\"For large refugee-flow corridors, a parsimonious model using only Google Trends variables can be employed, benefiting from close-to-real-time availability.\"}]","Forecasting Bilateral Refugee Flows with High-dimensional Data and Machine Learning Techniques - Research Report | PDF",1785894862,123,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"forecasting-bilateral-refugee-flows-with-high-dimensional-data-and-machine-learning-techniques-research-report","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/forecasting-bilateral-refugee-flows-with-high-dimensional-data-and-machine-learning-techniques-research-report/124828/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-05",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What data and modeling approach are used to forecast refugee flows?","Question",{"text":75,"@type":76},"The study builds monthly forecasting models for 150 origin countries to the EU27 using machine learning and high-dimensional data, including digital trace data from Google Trends.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which ensemble method performs best and for what horizon range?",{"text":80,"@type":76},"An ensemble forecast combining Random Forest and Extreme Gradient Boosting consistently outperforms other models for forecast horizons between 3 and 12 months.",{"name":82,"@type":73,"acceptedAnswer":83},"How can forecasting be done in near real time for large corridors?",{"text":84,"@type":76},"For large refugee-flow corridors, a parsimonious model using only Google Trends variables can be employed, benefiting from close-to-real-time availability.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]