Deep Reinforcement Learning for Active High Frequency Trading

TL;DR

This paper presents a novel end-to-end deep reinforcement learning framework for high frequency stock trading, demonstrating that agents can learn profitable strategies from high-frequency Limit Order Book data.

Contribution

It introduces the first DRL-based approach for active high frequency trading, employing PPO and hyperparameter tuning on real market data.

Findings

Agents can develop dynamic representations of market environments.

Trained agents achieve stable positive returns in stochastic, non-stationary markets.

Selective training on large price changes enhances learning effectiveness.

Abstract

We introduce the first end-to-end Deep Reinforcement Learning (DRL) based framework for active high frequency trading in the stock market. We train DRL agents to trade one unit of Intel Corporation stock by employing the Proximal Policy Optimization algorithm. The training is performed on three contiguous months of high frequency Limit Order Book data, of which the last month constitutes the validation data. In order to maximise the signal to noise ratio in the training data, we compose the latter by only selecting training samples with largest price changes. The test is then carried out on the following month of data. Hyperparameters are tuned using the Sequential Model Based Optimization technique. We consider three different state characterizations, which differ in their LOB-based meta-features. Analysing the agents' performances on test data, we argue that the agents are able to create a dynamic representation of the underlying environment. They identify occasional regularities present in the data and exploit them to create long-term profitable trading strategies. Indeed, agents learn trading strategies able to produce stable positive returns in spite of the highly stochastic and non-stationary environment.