arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2312.09353q-fin.TRq-fin.CP
收藏

带有自注意力的残差U-net求解多智能体时间一致最优交易执行问题

Residual U-net with Self-Attention to Solve Multi-Agent Time-Consistent Optimal Trade Execution

Andrew Na, Justin Wan

AI总结:

本文提出带自注意力的残差U-net求解多智能体多资产的时间一致均值方差最优交易执行问题,克服有限差分局限,并分析价格冲击与不同经济条件下的最优策略。

摘要:

本文探讨了使用带有自注意力的深度残差U-net来求解多智能体和多资产下的连续时间、时间一致均值方差最优交易执行问题。在有限时间范围内,我们基于Almgren-Chriss模型,将时间一致均值方差最优交易执行问题表述为Hamilton-Jacobi-Bellman(HJB)方程。已知HJB公式对未知值函数具有粘性解。我们将HJB方程重新表述为倒向随机微分方程(BSDE),以将问题扩展到多智能体和多资产情形。我们利用带有自注意力的残差U-net来数值逼近多智能体和多资产的值函数,该值函数可用于确定时间一致的最优控制。在本文中,我们展示了所提出的神经网络方法克服了有限差分方法的局限性。我们验证了结果并研究了参数敏感性。利用我们的框架,我们研究了一个具有显著价格冲击的智能体与一个没有价格冲击的智能体之间的相互作用,以及两类智能体所采用的最优策略。我们还研究了多个卖方和买方在不同经济条件下的表现,并将其与持有策略进行比较。

英文摘要:

In this paper, we explore the use of a deep residual U-net with self-attention to solve the the continuous time time-consistent mean variance optimal trade execution problem for multiple agents and assets. Given a finite horizon we formulate the time-consistent mean-variance optimal trade execution problem following the Almgren-Chriss model as a Hamilton-Jacobi-Bellman (HJB) equation. The HJB formulation is known to have a viscosity solution to the unknown value function. We reformulate the HJB to a backward stochastic differential equation (BSDE) to extend the problem to multiple agents and assets. We utilize a residual U-net with self-attention to numerically approximate the value function for multiple agents and assets which can be used to determine the time-consistent optimal control. In this paper, we show that the proposed neural network approach overcomes the limitations of finite difference methods. We validate our results and study parameter sensitivity. With our framework we study how an agent with significant price impact interacts with an agent without any price impact and the optimal strategies used by both types of agents. We also study the performance of multiple sellers and buyers and how they compare to a holding strategy under different economic conditions.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑