Reinforcement Learning for Systematic FX Trading

TL;DR

This paper presents a reinforcement learning approach for systematic foreign exchange trading, utilizing transfer learning to improve trading performance while accounting for transaction and funding costs over a 7-year period.

Contribution

It introduces a novel transfer learning method from Gaussian mixture models to reinforcement learning for FX trading, enhancing risk targeting and trading efficiency.

Findings

Achieved an annualized portfolio information ratio of 0.52.

Generated a 9.3% compound return over 7 years.

Successfully incorporated transaction and funding costs into the trading model.

Abstract

We explore online inductive transfer learning, with a feature representation transfer from a radial basis function network formed of Gaussian mixture model hidden processing units to a direct, recurrent reinforcement learning agent. This agent is put to work in an experiment, trading the major spot market currency pairs, where we accurately account for transaction and funding costs. These sources of profit and loss, including the price trends that occur in the currency markets, are made available to the agent via a quadratic utility, who learns to target a position directly. We improve upon earlier work by targeting a risk position in an online transfer learning context. Our agent achieves an annualised portfolio information ratio of 0.52 with a compound return of 9.3\%, net of execution and funding cost, over a 7-year test set; this is despite forcing the model to trade at the close of the trading day at 5 pm EST when trading costs are statistically the most expensive.