Conditional Generators for Limit Order Book Environments: Explainability, Challenges, and Robustness. (arXiv:2306.12806v1 [q-fin.TR])
By: <a href="http://arxiv.org/find/q-fin/1/au:+Coletta_A/0/1/0/all/0/1">Andrea Coletta</a>, <a href="http://arxiv.org/find/q-fin/1/au:+Jerome_J/0/1/0/all/0/1">Joseph Jerome</a>, <a href="http://arxiv.org/find/q-fin/1/au:+Savani_R/0/1/0/all/0/1">Rahul Savani</a>, <a href="http://arxiv.org/find/q-fin/1/au:+Vyetrenko_S/0/1/0/all/0/1">Svitlana Vyetrenko</a> Posted: June 23, 2023
Limit order books are a fundamental and widespread market mechanism. This
paper investigates the use of conditional generative models for order book
simulation. For developing a trading agent, this approach has drawn recent
attention as an alternative to traditional backtesting due to its ability to
react to the presence of the trading agent. Using a state-of-the-art CGAN (from
Coletta et al. (2022)), we explore its dependence upon input features, which
highlights both strengths and weaknesses. To do this, we use “adversarial
attacks” on the model’s features and its mechanism. We then show how these
insights can be used to improve the CGAN, both in terms of its realism and
robustness. We finish by laying out a roadmap for future work.
Provided by:
http://arxiv.org/icons/sfx.gif
