Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
134 tokens/sec
GPT-4o
10 tokens/sec
Gemini 2.5 Pro Pro
47 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Conditional Generators for Limit Order Book Environments: Explainability, Challenges, and Robustness (2306.12806v1)

Published 22 Jun 2023 in q-fin.TR, cs.AI, cs.CE, and cs.LG

Abstract: 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.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (59)
  1. Optimal execution of portfolio transactions. Journal of Risk, 3:5–40, 2001.
  2. Wasserstein generative adversarial networks. In International conference on machine learning, pages 214–223. PMLR, 2017.
  3. Recurrent conditional generative adversarial networks for autonomous driving sensor modelling. In Proc. of ITSC, pages 1613–1618, 2019.
  4. Conditional generative adversarial networks for modelling fuel sprays. Energy and AI, 12:100216, 2023.
  5. Market impacts and the life cycle of investors orders. Market Microstructure and Liquidity, 1(02):1550009, 2015.
  6. Efficient calibration of multi-agent simulation models from output series with bayesian optimization. In Proc. of ICAIF, pages 437–445, 2022.
  7. How to evaluate trading strategies: Single agent market replay or multiple agent interactive simulation? CoRR, abs/1906.12010, 2019.
  8. Evasion attacks against machine learning at test time. In Machine Learning and Knowledge Discovery in Databases: European Conference, ECML PKDD 2013, Prague, Czech Republic, September 23-27, 2013, Proceedings, Part III 13, pages 387–402. Springer, 2013.
  9. Ali Borji. Pros and cons of GAN evaluation measures. Computer Vision and Image Understanding, 179:41–65, 2019.
  10. Trades, quotes and prices: financial markets under the microscope. Cambridge University Press, 2018.
  11. Jean-Philippe Bouchaud. Price impact. arXiv preprint arXiv:0903.2428, 2009.
  12. A data-driven market simulator for small data environments. CoRR, abs/2006.14498, 2020.
  13. Flowgan: A conditional generative adversarial network for flow prediction in various conditions. In Proc. of ICTAI, pages 315–322, 2020.
  14. Towards realistic market simulations: a generative adversarial networks approach. In Proc. of ICAIF, pages 46:1–46:9, 2021.
  15. Learning to simulate realistic limit order book markets from data as a world agent. In Proc. of ICAIF, pages 428–436, 2022.
  16. K-SHAP: Policy clustering algorithm for anonymous state-action pairs. arXiv preprint arXiv:2302.11996, 2023.
  17. Diffusion models in vision: A survey. arXiv preprint arXiv:2209.04747, 2022.
  18. Real-valued (medical) time series generation with recurrent conditional gans. CoRR, abs/1706.02633, 2017.
  19. Market making with signals through deep reinforcement learning. IEEE Access, 9:61611–61622, 2021.
  20. Generative Adversarial Nets. In Proc. of NIPS, 2014.
  21. Generative adversarial networks. Communications of the ACM, 63(11):139–144, 2020.
  22. Limit Order Books. Quantitative Finance, 13(11):1709–1742, 2013.
  23. Improved training of wasserstein gans. Advances in neural information processing systems, 30, 2017.
  24. The market impact of a limit order. Journal of Economic Dynamics and Control, 36(4):501–522, 2012.
  25. Denoising diffusion probabilistic models. Advances in Neural Information Processing Systems, 33:6840–6851, 2020.
  26. Large-block transactions, the speed of response, and temporary and permanent stock-price effects. Journal of Financial Economics, 26(1):71–95, 1990.
  27. Lobster: Limit order book reconstruction system. Available at SSRN 1977207, 2011.
  28. Market making with scaled beta policies. In Proc. of ICAIF, pages 214–222, 2022.
  29. Improving generalization in reinforcement learning-based trading by using a generative adversarial market model. IEEE Access, 9:50738–50754, 2021.
  30. Agent-based model calibration using machine learning surrogates. Journal of Economic Dynamics and Control, 90:366–389, 2018.
  31. Generating realistic stock market order streams. In Proc. of AAAI, pages 727–734, 2020.
  32. The (mis) behaviour of markets: a fractal view of risk, ruin and reward. Profile books, 2010.
  33. Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784, 2014.
  34. Reinforcement learning for optimized trade execution. In Proc. of ICML, pages 673–680, 2006.
  35. Deep neural networks are easily fooled: High confidence predictions for unrecognizable images. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 427–436, 2015.
  36. Double deep q-learning for optimal execution. Applied Mathematical Finance, 28(4):361–380, 2021.
  37. Alexander Outkin. An agent-based model of the nasdaq stock market : Historic validation and future directions. 2012.
  38. Robert Pardo. The Evaluation and Optimization of Trading Strategies, 2nd Edition. Wiley, 2008.
  39. Robust adversarial reinforcement learning. In Proc. of ICML, volume 70, pages 2817–2826, 2017.
  40. The problem of calibrating an agent-based model of high-frequency trading. CoRR, abs/1606.01495, 2017.
  41. Donovan Platt. A comparison of economic agent-based model calibration methods. Journal of Economic Dynamics and Control, 113:103859, 2020.
  42. Autoregressive denoising diffusion models for multivariate probabilistic time series forecasting. In ICML, volume 139, pages 8857–8868, 2021.
  43. Multivariate probabilistic time series forecasting via conditioned normalizing flows. In ICLR, 2021.
  44. Learning to simulate. In ICLR (Poster). OpenReview.net, 2019.
  45. Rahul Savani. High-Frequency Trading: The Faster, the Better? IEEE Intelligent Systems, 27(4):70–73, 2012.
  46. Neural stochastic agent-based limit order book simulation: A hybrid methodology. In AAMAS 2023, the 22nd International Conference on Autonomous Agents and Multiagent Systems, 2023.
  47. Justin A Sirignano. Deep learning for limit order books. Quantitative Finance, 19(4):549–570, 2019.
  48. Learning structured output representation using deep conditional generative models. In Proc. of NIPS, pages 3483–3491, 2015.
  49. Robust Market Making via Adversarial Reinforcement Learning. Proc. of IJCAI, 2020.
  50. Market Making via Reinforcement Learning. In Proc. of AAMAS, pages 434–442, 2018.
  51. Data-snooping, technical trading rule performance, and the bootstrap. The Journal of Finance, 54(5):1647–1691, 1999.
  52. Trafficsim: Learning to simulate realistic multi-agent behaviors. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 10400–10409, 2021.
  53. Intriguing properties of neural networks. arXiv preprint arXiv:1312.6199, 2013.
  54. Get real: realism metrics for robust limit order book market simulations. In ICAIF, pages 2:1–2:8. ACM, 2020.
  55. Towards robust representation of limit orders books for deep learning models. arXiv preprint arXiv:2110.05479, 2022.
  56. Modeling tabular data using conditional GAN. In NeurIPS, pages 7333–7343, 2019.
  57. Beyond the square root: Evidence for logarithmic dependence of market impact on size and participation rate. Market Microstructure and Liquidity, 1(02):1550004, 2015.
  58. Deeplob: Deep convolutional neural networks for limit order books. IEEE Transactions on Signal Processing, 67(11):3001–3012, 2019.
  59. Price jump prediction in limit order book. arXiv preprint arXiv:1204.1381, 2012.
Citations (13)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now