Can Machine Learning Help Predict the Outcome of Asylum Adjudications?

Proceedings of the ACM Conference on AI and the Law, 2017

12 Pages Posted: 30 Jul 2016 Last revised: 20 Apr 2020

See all articles by Daniel L. Chen

Daniel L. Chen

Directeur de Recherche, Centre National de la Recherche Scientifique, Toulouse School of Economics, Institute for Advanced Study in Toulouse, University of Toulouse Capitole, Toulouse, France

Jess Eagel

NYU Courant Institute of Mathematical Sciences

Date Written: December 30, 2016

Abstract

In this study, we analyzed 492,903 asylum hearings from 336 different hearing locations, rendered by 441 unique judges over a thirty-two year period from 1981-2013. We define the problem of asylum adjudication prediction as a binary classification task, and using the random forest method developed by Breiman (2001), we predict twenty-seven years of refugee decisions. Using only data available up to the decision date, our model correctly classifies 82 percent of all refugee cases by 2013. Our empirical analysis suggests that decision makers exhibit a fair degree of autocorrelation in their rulings, and extraneous factors such as, news and the local weather may be impacting the fate of an asylum seeker. Surprisingly, granting asylum is predominantly driven by trend features and judicial characteristics- features that may seem unfair- and roughly one third-driven by case information, news events, and court information.

Keywords: Quantitative legal prediction, Refugee, Machine learning

Suggested Citation

Chen, Daniel L. and Eagel, Jess, Can Machine Learning Help Predict the Outcome of Asylum Adjudications? (December 30, 2016). Proceedings of the ACM Conference on AI and the Law, 2017, Available at SSRN: https://ssrn.com/abstract=2815876 or http://dx.doi.org/10.2139/ssrn.2815876

Daniel L. Chen

Directeur de Recherche, Centre National de la Recherche Scientifique, Toulouse School of Economics, Institute for Advanced Study in Toulouse, University of Toulouse Capitole, Toulouse, France ( email )

Toulouse School of Economics
1, Esplanade de l'Université
Toulouse, 31080
France

Jess Eagel (Contact Author)

NYU Courant Institute of Mathematical Sciences ( email )

Here is the Coronavirus
related research on SSRN

Paper statistics

Downloads
214
Abstract Views
1,352
rank
157,418
PlumX Metrics