Deep Calibration of Multi-Agent Model for Simulating Real-World Stock Trading

Abstract: Multi-agent market model is a stock trading simulation system, which generates order flow given the agent variable of the model. We study calibrating the agent variable to simulate the order flow of any given historical trading day. In contrast to the traditional calibration that relies on the inefficient iterative search, we propose DeepCal, the first search-free approach that uses deep learning to calibrate multi-agent market model. DeepCal learns from a novel surrogate-trading loss function to address the non-differentiable issue induced by the multi-agent model and introduces a condition-aware variable estimator, adapting the trading simulation to different market conditions to enhance explainability. Through extensive experiments on real order-book data over a whole year, DeepCal has demonstrated comparable simulation accuracy (<0.36 in Kolmogorov-Smirnov statistic) to traditional search-based approaches without the need for variable search, and can effectively capture the correlation between agent variable and multiple market-condition indexes~(PPI, PMI, CPI, market trend and market noise).