arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2204.08581q-fin.TRcs.LGq-fin.CP
收藏

关于参数化最优执行与机器学习代理模型的研究

On Parametric Optimal Execution and Machine Learning Surrogates

University of Michigan(密歇根大学);University of California Santa Barbara(加州大学圣塔芭芭拉分校);University of California Los Angeles(加州大学洛杉矶分校)

Tao Chen, Mike Ludkovski, Moritz Voß

AI总结:

本文研究离散时间最优订单执行问题,在线性价格冲击下推导闭式递推公式,并针对非线性情形提出基于actor-critic框架的神经网络代理模型,实现跨参数配置的准确策略逼近。

摘要:

我们研究离散时间下具有瞬时价格冲击和随机恢复力的最优订单执行问题。首先,在线性瞬时价格冲击的设定下,我们推导出最优策略的闭式递推公式,扩展了Obizhaeva和Wang(J Financial Markets, 2013)的确定性结果。其次,针对Bouchaud等人(Quant. Finance, 2004)提出的非线性瞬时价格冲击情形,我们开发了一种基于动态规划和深度学习的数值算法。具体而言,我们采用actor-critic框架,为价值函数和反馈控制分别构建两个神经网络(NN)代理模型。神经网络函数逼近器的灵活可扩展性使得参数化学习成为可能,即将若干模型或市场参数纳入输入空间。价格冲击、恢复力等参数的精确校准被认为极具挑战性,因此理解执行策略对这些参数的敏感性至关重要。我们的神经网络学习器能够在多个输入维度上自然扩展,并能在广泛的参数配置范围内准确逼近最优策略。我们提供了一个完全可复现的Jupyter Notebook,其中包含我们的神经网络实现,这具有独立的教学意义,展示了神经网络代理模型在(参数化)随机控制问题中的易用性。

英文摘要:

We investigate optimal order execution problems in discrete time with instantaneous price impact and stochastic resilience. First, in the setting of linear transient price impact we derive a closed-form recursion for the optimal strategy, extending the deterministic results from Obizhaeva and Wang (J Financial Markets, 2013). Second, we develop a numerical algorithm based on dynamic programming and deep learning for the case of nonlinear transient price impact as proposed by Bouchaud et al. (Quant. Finance, 2004). Specifically, we utilize an actor-critic framework that constructs two neural-network (NN) surrogates for the value function and the feedback control. The flexible scalability of NN functional approximators enables parametric learning, i.e., incorporating several model or market parameters as part of the input space. Precise calibration of price impact, resilience, etc., is known to be extremely challenging and hence it is critical to understand sensitivity of the execution policy to these parameters. Our NN learner organically scales across multiple input dimensions and is shown to accurately approximate optimal strategies across a wide range of parameter configurations. We provide a fully reproducible Jupyter Notebook with our NN implementation, which is of independent pedagogical interest, demonstrating the ease of use of NN surrogates in (parametric) stochastic control problems.

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。

↑