Optimal Trading in Automated Market Makers with Deep Learning

TL;DR

This paper develops a deep learning-based method to optimize trading strategies in CFMMs and centralized exchanges, effectively managing market interaction and order hiding without approximations.

Contribution

It introduces a novel model combining market interactions with a deep Galerkin approach to solve complex dynamic programming equations for optimal trading.

Findings

Optimal strategies avoid price slippage.

Deep Galerkin method effectively solves intractable equations.

Proposed strategies outperform naive approaches.

Abstract

This article explores the optimisation of trading strategies in Constant Function Market Makers (CFMMs) and centralised exchanges. We develop a model that accounts for the interaction between these two markets, estimating the conditional dependence between variables using the concept of conditional elicitability. Furthermore, we pose an optimal execution problem where the agent hides their orders by controlling the rate at which they trade. We do so without approximating the market dynamics. The resulting dynamic programming equation is not analytically tractable, therefore, we employ the deep Galerkin method to solve it. Finally, we conduct numerical experiments and illustrate that the optimal strategy is not prone to price slippage and outperforms na\"ive strategies.