Deep Reinforcement Learning for Tick-Level Crypto Market Making

Summary

The document presents a high-frequency market-making framework that combines tick-level market data with periodic prediction signals. It applies deep reinforcement learning to use both fast order-level information and less frequent forecasts when setting market-making actions. The motivation is that high-volume tick data and complex market conditions make it difficult to build effective liquidity-provision strategies from a single information source.

The reported evaluation compares strategies built with different deep reinforcement learning algorithms in simulated scenarios and experiments using real cryptocurrency market data. The authors say the combined framework improves profitability and risk management relative to existing methods. The summary does not identify the specific algorithms, assets, evaluation periods, baselines, or risk measures, so the size and generality of the reported gains cannot be assessed from this description alone.

Key ideas

• The proposed market-making approach combines tick-level observations with periodic prediction signals.
• Deep reinforcement learning maps the combined information into market-making decisions.
• The framework is motivated by the volume and complexity of high-frequency market data.
• Simulations and real cryptocurrency data are used to assess strategies across reinforcement learning algorithms.
• The document reports profitability and risk-management improvements, but omits details needed to gauge their scale or generality.

Tags

# Integrating Tick-level Data and Periodical Signal for High-frequency Market Making


# Integrating Tick-level Data and Periodical Signal for High-frequency Market Making









We focus on the problem of market making in high-frequency trading. Market making is a critical function in financial markets that involves providing liquidity by buying and selling assets. However, the increasing complexity of financial markets and the high volume of data generated by tick-level trading makes it challenging to develop effective market making strategies. To address this challenge, we propose a deep reinforcement learning approach that fuses tick-level data with periodic prediction signals to develop a more accurate and robust market making strategy. Our results of market making strategies based on different deep reinforcement learning algorithms under the simulation scenarios and real data experiments in the cryptocurrency markets show that the proposed framework outperforms existing methods in terms of profitability and risk management.

Shown in full with attribution under the source's licence. Licence: abstract CC0

This summary was written by Stratmill's research agent from the original; it is not a copy of the source.