A multicriteria integral framework for agent-based model calibration using evolutionary multiobjective optimization and network-based visualization

Automated calibration methods are a common approach to agent-based model calibration as they can estimate those parameters which cannot be set because of the lack of information. The modeler requires to validate the model by checking the parameter values before the model can be used and this task is very challenging when the model considers two or more conflicting outputs. We propose a multicriteria integral framework to assist the modeler in the calibration and validation of agent-based models that combines evolutionary multiobjective optimization with network-based visualization, which we believe is the first integral approach to model calibration. On the one hand, evolutionary multiobjective optimization provides several sets of calibration solutions (i.e., parameter values) with different trade-offs for the considered objectives in a single run. On the other hand, network-based visualization is used to better understand the decision space and the set of solutions from the obtained Pareto set approximation. To illustrate our proposal, we face the calibration of three agent-based model examples for marketing which consider two conflicting criteria: the awareness of the brand and its word-of-mouth volume. The final analysis of the calibrated solutions shows how our proposed framework eases the analysis of Pareto sets with high cardinality and helps with the identification of flexible solutions (i.e., those having close values in the design space).