Data can aid our understanding of refugee flows and, consequently, help in providing aid to refugees. Building on a model created by the British Red Cross, we develop an improved model that serves as a prototype for further efforts in this area.
In September 2015, the British Red Cross (BRC) developed a model to anticipate refugee flows in Europe. Such models are useful to aid organisations due to the insight they offer into the volume of refugees and the routes they travel. In turn, this allows for strategic planning of goods (e.g. foodstuffs, blankets and medicines) and volunteers to areas that are most likely to need them.
The model created by the BRC is based on count data published by the United Nations High Commisioner for Refugees (UNHCR). The results were generally regarded as positive but found to be more stable for countries that are situated closer to the final destination of refugees. We perform several exploratory analyses aimed improving our understanding of the UNHCR data and improving the initial model created by the BRC.
The Leiden University Centre for Innovation (CFI) was asked to explore the UNHCR data and, if possible, improve on the original BRC model. Concretely, our goals were as follows:
- Gain a better understanding of the count data. That is, try to better understand its limitations.
- Outperform the BRC model in prediction accuracy and robustness.
- Find a way to predict refugee arrivals at least two days ahead.
Our model substantially improved both prediction accuracy and the ability to follow increases/decreases in refugee arrivals for the test period.
Our model was also able to predict more than one day ahead. The entire write-up can be found here.
Future work will focus on combining the data used for this project with ancillary data and to incorporate the ability to experiment with ‘what if’ scenarios.
The files needed to reproduce our analyses can be found on GitHub and are available here.
This project was developed by the Leiden University Centre for Innovation (Peace Informatics Lab) in collaboration with RISA-IT.
This is a project designed and delivered by CFI's HumanityX team, with support of HumanityX partners and with financial assistance by the City of The Hague. See HumanityX website for related projects.
For further information, contact Arvid Halma (email@example.com)