DeepScalper: A Risk-Aware Reinforcement Learning Framework to Capture Fleeting Intraday Trading Opportunities

TL;DR

DeepScalper introduces a risk-aware reinforcement learning framework tailored for intraday trading, effectively capturing fleeting opportunities by modeling multi-modality market data and balancing profit with risk.

Contribution

The paper presents a novel RL framework with a dueling Q-network, a new reward function, multi-modality market embedding, and risk-aware auxiliary tasks for intraday trading.

Findings

Outperforms state-of-the-art baselines on real market data.

Effectively captures intraday market dynamics and fleeting opportunities.

Balances profit maximization with risk minimization.

Abstract

Reinforcement learning (RL) techniques have shown great success in many challenging quantitative trading tasks, such as portfolio management and algorithmic trading. Especially, intraday trading is one of the most profitable and risky tasks because of the intraday behaviors of the financial market that reflect billions of rapidly fluctuating capitals. However, a vast majority of existing RL methods focus on the relatively low frequency trading scenarios (e.g., day-level) and fail to capture the fleeting intraday investment opportunities due to two major challenges: 1) how to effectively train profitable RL agents for intraday investment decision-making, which involves high-dimensional fine-grained action space; 2) how to learn meaningful multi-modality market representation to understand the intraday behaviors of the financial market at tick-level. Motivated by the efficient workflow of professional human intraday traders, we propose DeepScalper, a deep reinforcement learning framework for intraday trading to tackle the above challenges. Specifically, DeepScalper includes four components: 1) a dueling Q-network with action branching to deal with the large action space of intraday trading for efficient RL optimization; 2) a novel reward function with a hindsight bonus to encourage RL agents making trading decisions with a long-term horizon of the entire trading day; 3) an encoder-decoder architecture to learn multi-modality temporal market embedding, which incorporates both macro-level and micro-level market information; 4) a risk-aware auxiliary task to maintain a striking balance between maximizing profit and minimizing risk. Through extensive experiments on real-world market data spanning over three years on six financial futures, we demonstrate that DeepScalper significantly outperforms many state-of-the-art baselines in terms of four financial criteria.