Automatic calibration of dynamic and heterogeneous parameters in agent-based models

Simulation has been applied to diverse domains such as urban growth modeling and market dynamics modeling. Some of these applications may require validations, based on some real-world observations modeled in the simulation. This validation can be conducted as either qualitative face-validation or quantitative empirical validation; however, as the importance and accumulation of data grows, the importance of quantitative validation has been highlighted in recent studies. The key component of quantitative validation is finding a calibrated set of parameters to regenerate the real-world observations in the simulation models. While the parameter of interest to be calibrated has hitherto been fixed throughout simulation executions, we expand the static parameter calibration in two dimensions in this study, dynamically and heterogeneously. The dynamic calibration changes the parameter values over the simulation period by reflecting the simulation output trend, and the heterogeneous calibration changes the parameter values per simulated entity clusters by considering the similarities of the entity states. We experimented with the proposed calibrations on a hypothetical case and a real-world case. For the hypothetical scenario, we used the wealth distribution model to illustrate how our calibration works. For the real-world scenario, we selected the real estate market model. The models were selected, because of two reasons. First, they have heterogeneous entities, being agent-based models. Second, they are agent-based models exhibiting real-world trends over time.