Machine learning simulates agent-based model towards optimal policy: A surrogate model for public policy assessment

Public policies are not intrinsically positive or negative. Rather, policies provide varying levels of effects across different recipients. Methodologically, computational modeling enables the application of a combination of multiple influences on empirical data, thus allowing for heterogeneous response to policies. We use a random forest machine learning algorithm to emulate an agentbased model (ABM) and evaluate competing policies across 46 Metropolitan Regions (MRs) in Brazil. In doing so, we use input parameters and output indicators of 11,076 actual simulation runs and one million emulated runs. As a result, we obtain the optimal (and non-optimal) performance of each region over the policies. Optimum is defined as a combination of production and inequality indicators for the full ensemble of MRs. Results suggest that MRs already have embedded structures that favor optimal or non-optimal results, but they also illustrate which policy is more beneficial to each place. In addition to providing MR-specific policies' results, the use of machine learning to simulate an ABM reduces the computational burden, whereas allowing for a much larger variation among model parameters. The coherence of results within the context of larger uncertainty - vis-à-vis those of the original ABM - suggests an additional test of robustness of the model. At the same time the exercise indicates which parameters should policymakers intervene, in order to work towards precise policy optimal instruments.