Unintended impacts of automation for integration? Simulating integration outcomes of algorithm-based refugee allocation in Germany

The location to which refugees are assigned upon arrival in a host country is a critical factor for their integration prospects. Several research groups have developed algorithmic tools based on artificial intelligence (AI) to optimize refugee-location matching, with the overall aim of improving refugees’ integration into the labor market. These tools are used in a highly sensitive context, and thus their design, social impacts, and potential long-term consequences need to be systematically assessed. To investigate such effects, we propose an agent-based simulation framework, grounded in sociological theory and real-world survey data. This framework allows for simulating different allocation mechanisms for refugees to locations and studying their impacts on integration outcomes. We illustrate the simulation framework in the German context by comparing the current approach of the Königsteiner Schlüssel (i.e., quasi-random allocation) with algorithm-based matching. We study each procedure’s impact on both economic and social integration and assess structural effects on inequalities between subgroups of refugees. We find that (1) algorithmic assignment can improve both economic and social integration outcomes globally; (2) performance gains vary geographically and demographically, potentially reinforcing existing inequalities; (3) incorporating feedback loops—where each allocation round reshapes local community composition—is crucial for assessing the impacts of algorithmic allocation systems in dynamic social environments.