Automatic Calibration Framework of Agent-Based Models for Dynamic and Heterogeneous Parameters
This work addresses the need for more accurate and efficient calibration in agent-based modeling, which is incremental as it builds on existing validation techniques.
The study tackled the problem of validating agent-based models by introducing an automatic calibration framework that combines dynamic and heterogeneous methods to adjust simulation parameters, resulting in improved alignment with real-world data through time-based and cluster-wise adjustments.
Agent-based models (ABMs) highlight the importance of simulation validation, such as qualitative face validation and quantitative empirical validation. In particular, we focused on quantitative validation by adjusting simulation input parameters of the ABM. This study introduces an automatic calibration framework that combines the suggested dynamic and heterogeneous calibration methods. Specifically, the dynamic calibration fits the simulation results to the real-world data by automatically capturing suitable simulation time to adjust the simulation parameters. Meanwhile, the heterogeneous calibration reduces the distributional discrepancy between individuals in the simulation and the real world by adjusting agent related parameters cluster-wisely.