SimLOB: Learning Representations of Limited Order Book for Financial Market Simulation

Yuanzhe Li^†, Yue Wu^†, Muyao Zhong, Shengcai Liu, Peng Yang.

IEEE Transactions on Artificial Intelligence. Accepted.

† Equal contribution (co-first authors).

Paper

Overview

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.

All publications & manuscripts →