On parametric optimal execution and machine learning surrogates

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 [Optimal trading strategy and supply/demand dynamics. J. Financial Mark., 2013, 16(1), 1-32]. 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. [Fluctuations and response in financial markets: The subtle nature of 'random' price changes. Quant. Finance, 2004, 4(2), 176-190]. 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 the 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.

Automated summary

This article investigates optimal order execution problems in discrete time with instantaneous price impact and stochastic resilience. It derives a closed-form recursion for the optimal strategy in the setting of linear transient price impact and develops a numerical algorithm based on dynamic programming and deep learning for the case of nonlinear transient price impact. The study shows that neural network functional approximators can accurately approximate optimal strategies.