MacroHFT: Memory Augmented Context-aware Reinforcement Learning On High Frequency Trading
By Chuqiao Zong, Chaojie Wang, Molei Qin, Lei Feng, Xinrun Wang, Bo An
Rating
1377
Battle Count: 87
Relevance
9/10
Highly relevant to high-frequency trading in cryptocurrency markets, with potential applications in other financial markets.
Implementation Complexity
7/10
Requires implementation of hierarchical reinforcement learning, memory augmentation, and context-aware learning, which may be complex for practitioners without advanced ML expertise.
Reproducibility
4/5
The paper provides detailed methodology and experiment setup. Code has been released on GitHub.
About this paper
Methodology: MacroHFT. Problem types: Reinforcement Learning, Time Series Forecasting, Algorithmic Trading.
The interactive Everscope explorer (charts, battles, favorites) loads below.