🤖 AI Summary
Existing financial market simulation (FMS) approaches generate limit order book (LOB) data with low fidelity, often calibrating only the mid-price and thereby losing critical microstructural information. Method: This paper introduces, for the first time, a fully end-to-end learnable representation framework that explicitly incorporates structured LOB time-series data. We propose a Transformer-based autoencoder that integrates LOB-structure-aware embeddings and a vector-space calibration objective, jointly modeling level-wise dependencies and nonlinear temporal autocorrelations. Contribution/Results: Experiments demonstrate that the learned representations significantly improve LOB-level fitting accuracy, simultaneously capturing microstructural dynamics and cross-level interactions. Calibration performance strongly correlates with representation quality, establishing a new paradigm for high-fidelity, LOB-driven market simulation.
📝 Abstract
Financial market simulation (FMS) serves as a promising tool for understanding market anomalies and the underlying trading behaviors. To ensure high-fidelity simulations, it is crucial to calibrate the FMS model for generating data closely resembling the observed market data. Previous efforts primarily focused on calibrating the mid-price data, leading to essential information loss of the market activities and thus biasing the calibrated model. The Limit Order Book (LOB) data is the fundamental data fully capturing the market micro-structure and is adopted by worldwide exchanges. However, LOB is not applicable to existing calibration objective functions due to its tabular structure not suitable for the vectorized input requirement. This paper proposes to explicitly learn the vectorized representations of LOB with a Transformer-based autoencoder. Then the latent vector, which captures the major information of LOB, can be applied for calibration. Extensive experiments show that the learned latent representation not only preserves the non-linear auto-correlation in the temporal axis, but the precedence between successive price levels of LOB. Besides, it is verified that the performance of the representation learning stage is consistent with the downstream calibration tasks. Thus, this work also progresses the FMS on LOB data, for the first time.