Proposing Location-based Predictive Features for Modeling Refugee Counts

Authors

  • Esther Mead Southern Arkansas University https://orcid.org/0000-0002-3180-2239
  • Maryam Maleki California State University
  • Mohammad Arani University of Arkansas at Little Rock
  • Nitin Agarwal University of Arkansas at Little Rock

DOI:

https://doi.org/10.33182/ter.v1i1.2883

Keywords:

Data Science, Machine Learning, Predictive Modeling, Refugee Crisis

Abstract

Machine learning models to predict refugee crisis situations are still lacking. The model proposed in this work uses a set of predictive features that are indicative of the sociocultural, socioeconomic, and economic characteristics that exist within each country and region. Twenty-eight features were collected for specific countries and years. The feature set was tested in experiments using ordinary least squares regression based on regional subsets. Potential location-based features stood out in our results, such as the global peace index, access to electricity, access to basic water, media censorship, and healthcare. The model performed best for the region of Europe, wherein the features with the most predictive power included access to justice and homicide rate. Corruption features stood out in both Africa and Asia, while population features were dominant in the Americas. Model performance metrics are provided for each experiment. Limitations of this dataset are discussed, as are steps for future work.

Downloads

Published

2023-05-28

How to Cite

Mead, E., Maleki, M., Arani, M., & Agarwal, N. (2023). Proposing Location-based Predictive Features for Modeling Refugee Counts. Transnational Education Review, 1(1), 3–16. https://doi.org/10.33182/ter.v1i1.2883

Issue

Section

Articles