Dual-Stage Attention-Based Recurrent Neural Networks for Market Microstructure

Abstract

This paper applies the Dual-Stage Attention-Based Recurrent Neural Network(DA-RNN) model to predict future price movements using microstructure variables. We analyze whether microstructure variables have predictive power for future price movements, and what factors influence this predictive power. We find that microstructure variables possess predictive power against the direction of future price movements. This predictive power depends on how many uninformed traders exist in the market. Moreover, the importance of microstructure variables is negatively related to market liquidity. Thus, while microstructure variables are more important in severe market conditions with high transaction costs, the effect of trading on price dynamics depends on market structure.