Process learning of network interactions in market microstructures

In this paper, we explore new models for explaining trends in high frequency market data. Market depth information such as volume at different price levels is used to develop more robust prediction models than typical ones learned on aggregate trade data. The latter ignore many of the evolving interactions of the agent based network. In light of this, two learned models incorporating various levels of price depth information are compared with a naive trading strategy. We explore the added value of using market maker network data. The study finds that on average, using information from multiple price levels gives better trend prediction results.