Deep Investing in Kyle's Single Period Model

TL;DR

This paper employs deep neural networks to model and replicate the equilibrium behavior in Kyle's single period market microstructure model, demonstrating convergence to the theoretical equilibrium through appropriate architectures and training methods.

Contribution

It introduces a deep learning approach to simulate Kyle's model, showing neural networks can learn and reproduce the theoretical equilibrium in market microstructure.

Findings

Neural networks can replicate Kyle's equilibrium behavior.

Proper architectures and training lead to convergence.

Model provides insights into market microstructure dynamics.

Abstract

The Kyle model describes how an equilibrium of order sizes and security prices naturally arises between a trader with insider information and the price providing market maker as they interact through a series of auctions. Ever since being introduced by Albert S. Kyle in 1985, the model has become important in the study of market microstructure models with asymmetric information. As it is well understood, it serves as an excellent opportunity to study how modern deep learning technology can be used to replicate and better understand equilibria that occur in certain market learning problems. We model the agents in Kyle's single period setting using deep neural networks. The networks are trained by interacting following the rules and objectives as defined by Kyle. We show how the right network architectures and training methods lead to the agents' behaviour converging to the theoretical equilibrium that is predicted by Kyle's model.