The calibration of financial agent-based models

Abstract

Agent-based models, particularly those applied to financial markets, demonstrate the ability to produce realistic, simulated system dynamics, comparable to those observed in empirical investigations. Despite this, they remain fairly difficult to calibrate due to their tendency to be computationally expensive, even with recent advances in technology. For this reason, financial agent-based models are frequently validated by demonstrating an ability to reproduce well-known log return time series and central limit order book stylized facts, as opposed to being rigorously calibrated to transaction data. We thus apply an established financial agent-based model calibration framework to a number of intraday agent-based models employing realistic order matching procedures and demonstrate that while the parameters of these models rooted in market microstructure can indeed be meaningfully calibrated, those exclusively related to agent behaviors and incentives remain problematic, due to the presence of parameter degeneracies not identified by stylized fact-centric validation. We further argue that the observed parameter degeneracies are likely a consequence of the realistic matching processes employed in these models, which suggests that alternative approaches to linking data, phenomenology and market structure may be necessary and that the stylized fact-centric validation of intraday agent-based models is insufficient.