This study applies a state-of-the-art simulation-based inference framework with neural networks to estimate parameters of a labour market agent-based model. The model is based on job transition networks and is initialized with synthetic and real U.S. labour market data. The approach addresses computational constraints in exploring the parameter space.
The method is important for practical use of agent-based models in decision support, as it enables calibration of complex models on real data.
Translation and summary are machine-generated from the source. The full article is not republished; its rights belong to the source.
