The promising predictive power of machine learning (ML) models is encouraging a wide range of applications, but the weak interpretability of their black-box feature is a major obstacle to their application to finance. The large scale of limit order book (LOB) data provides fertile ground for ML...

This working paper was written by Kalok Chan (Chinese University of Hong Kong Business School), F.Y. Eric Lam (Independent Researcher)*, Giorgio Valente (Hong Kong Institute for Monetary and Financial Research) and Siyuan Wu (Chinese University of Hong Kong Business School).Trading venues have...