Financial Market Simulation (SimLOB)

Southern University of Science and Technology · July 2023–May 2024
Research Assistant · Advisor: Prof. Peng Yang

A Transformer-based autoencoder learns limit order book representations for multi-agent market calibration, achieving lower calibration errors than mid-price and raw-LOB approaches in 9 of 10 simulation scenarios.

IEEE Transactions on Artificial Intelligence. Accepted. Paper