Differentiable Planning for Optimal Liquidation

  • Alan A. Pennacchio USP
  • Leliane N. de Barros USP
  • Denis D. Mauá USP


Optimal liquidation consists of selling large blocks of single stocks within given time frames optimally with respect to specified risk-sensitive objectives. In this paper, we extend the Almgren-Chriss model for the liquidation process to a more generic and realistic setting and present a differentiable planning algorithm to solve it. We evaluate the performance of the proposed method through experiments, demonstrating the potential of differentiable planning for optimal liquidation in realistic scenarios.
Palavras-chave: Differentiable Planning, Risk-sensitive Objective, Markov Decision Process, Optimal Liquidation


Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G. S., Davis, A., Dean, J., Devin, M., Ghemawat, S., Goodfellow, I., Harp, A., Irving, G., Isard, M., Jia, Y., Jozefowicz, R., Kaiser, L., Kudlur, M., Levenberg, J., Mané, D., Monga, R., Moore, S., Murray, D., Olah, C., Schuster, M., Shlens, J., Steiner, B., Sutskever, I., Talwar, K., Tucker, P., Vanhoucke, V., Vasudevan, V., Viégas, F., Vinyals, O., Warden, P., Wattenberg, M., Wicke, M., Yu, Y., and Zheng, X. (2015). TensorFlow: Large-scale machine learning on heterogeneous systems. Software available from https://tensorflow.org.

Almgren, R. and Chriss, N. (2001). Optimal execution of portfolio transactions. Journal of Risk, 3:5–40.

Bradbury, J., Frostig, R., Hawkins, P., Johnson, M. J., Leary, C., Maclaurin, D., Necula, G., Paszke, A., VanderPlas, J., Wanderman-Milne, S., and Zhang, Q. (2018). JAX: composable transformations of Python+NumPy programs.

Bueno, T. P. (2021). Planning in stochastic computation graphs: solving stochastic nonlinear problems with backpropagation. PhD thesis, Universidade de São Paulo.

Bueno, T. P., de Barros, L. N., Mauá, D. D., and Sanner, S. (2019). Deep reactive policies for planning in stochastic nonlinear domains. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 33, pages 7530–7537.

Derman, E. and Kani, I. (1994). Riding on a smile. Risk, 7(2):32–39.

Dupire, B. et al. (1994). Pricing with a smile. Risk, 7(1):18–20.

Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep learning. MIT press.

Hull, J. C. (2006). Options, futures and other derivatives. Prentice Hall, Upper Saddle River, US, 6th ed edition.

Kingma, D. P. and Ba, J. (2015). Adam: A method for stochastic optimization. In 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings.

Robbins, H. and Monro, S. (1951). A stochastic approximation method. The annals of mathematical statistics, pages 400–407.

Wang, M., Fang, E. X., and Liu, H. (2017). Stochastic compositional gradient descent: algorithms for minimizing compositions of expected-value functions. Mathematical Programming, 161(1):419–449.

Wu, G., Say, B., and Sanner, S. (2017). Scalable planning with tensorflow for hybrid nonlinear domains. Advances in Neural Information Processing Systems, 30.
PENNACCHIO, Alan A.; BARROS, Leliane N. de; MAUÁ, Denis D.. Differentiable Planning for Optimal Liquidation. In: BRAZILIAN WORKSHOP ON ARTIFICIAL INTELLIGENCE IN FINANCE (BWAIF), 1. , 2022, Niterói. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2022 . p. 48-57. DOI: https://doi.org/10.5753/bwaif.2022.223144.