Paper: arXiv 2502.17417

Abstract

In this paper, we propose an event-driven Limit Order Book (LOB) model that captures twelve of the most observed LOB events in exchange-based financial markets. To model these events, we propose using the state-of-the-art Neural Hawkes process, a more robust alternative to traditional Hawkes process models. More specifically, this model captures the dynamic relationships between different event types, particularly their long- and short-term interactions, using a Long Short-Term Memory neural network. Using this framework, we construct a midprice process that captures the event-driven behavior of the LOB by simulating high-frequency dynamics like how they appear in real financial markets. The empirical results show that our model captures many of the broader characteristics of the price fluctuations, particularly in terms of their overall volatility. We apply this LOB simulation model within a Deep Reinforcement Learning Market-Making framework, where the trading agent can now complete trade order fills in a manner that closely resembles real-market trade execution. Here, we also compare the results of the simulated model with those from real data, highlighting how the overall performance and the distribution of trade order fills closely align with the same analysis on real data.

Complexity vs Empirical Score

  • Math Complexity: 8.5/10
  • Empirical Rigor: 7.0/10
  • Quadrant: Holy Grail — high math complexity, high empirical rigor

Why this score: The paper employs advanced mathematics, including Neural Hawkes processes, nonlinear multivariate point processes, and deep reinforcement learning, which is highly mathematically dense. Empirically, it uses real LOB data, compares simulated results to real markets, and applies the model to a practical market-making strategy, indicating strong backtest-readiness and implementation focus.

Research Flowchart

  flowchart TD
  A["Research Goal: Model LOB dynamics & apply to Market-Making"] --> B["Data: Exchange LOB Data\n(12 Event Types)"]
  B --> C["Methodology: Neural Hawkes Process\n(LSTM for temporal dynamics)"]
  C --> D["Computational Process: Event-Driven LOB Simulation"]
  D --> E["Output: Synthetic Midprice Process\n(Captures Volatility & Event Correlations)"]
  E --> F["Application: Deep Reinforcement Learning\nMarket-Making Agent"]
  F --> G["Key Outcomes: Validated Realism vs. Real Data\n(Trade Execution Distribution & Performance)"]

Cited References (93)

  1. Long-time behavior of a hawkes process–based limit order book (2015)
  2. Optimal execution of portfolio transactions (2001)
  3. A discussion paper for possible approaches to building a statistically valid backtesting framework (2024)
  4. Backtest overfitting in the machine learning era: A comparison of out-of-sample testing methods in a synthetic controlled environment (2024)
  5. Deep attentive survival analysis in limit order books: Estimating fill probabilities with convolutional-transformers (2024)
  6. Deep reinforcement learning: A brief survey (2017)
  7. High-frequency trading in a limit order book (2008)
  8. Hawkes processes in finance (2015)
and 85 more
  1. Market making and incentives design in the presence of a dark pool: a Stackelberg actor–critic approach (2023)
  2. The exploration-exploitation dilemma: a multidisciplinary framework (2014)
  3. Optimal control of execution costs (1998)
  4. The pricing of options and corporate liabilities (1973)
  5. Optimal control of trading algorithms: a general impulse control approach (2011)
  6. Price discovery without trading: Evidence from limit orders (2019)
  7. Optimal execution of limit and market orders with trade director, speed limiter, and fill uncertainty (2017)
  8. Enhancing trading strategies with order book signals (2018)
  9. Algorithmic and high-frequency trading (2015)
  10. Buy low, sell high: A high frequency trading perspective (2014)
  11. Algorithmic trading, stochastic control, and mutually exciting processes (2018)
  12. Deep reinforcement learning for algorithmic trading (2021)
  13. An electronic market-maker (2001)
  14. The price impact of order book events (2014)
  15. Price dynamics in a Markovian limit order market (2013)
  16. Portfolio selection with transaction costs (1990)
  17. Limit Order Book ( LOB ) shape modeling in presence of heterogeneously informed market participants (2019)
  18. The negative drift of a limit order fill — → 2407.16527
  19. High-Frequency Trading (2016) — link
  20. Flow toxicity and liquidity in a high-frequency world (2012)
  21. Semi- Markov model for market microstructure (2015)
  22. High frequency trading and asymptotics for small risk aversion in a Markov renewal model (2015)
  23. Taming the noise in reinforcement learning via soft updates (2015) — link
  24. Reinforcement learning approaches to optimal market making (2021)
  25. Deep reinforcement learning for market making under a Hawkes process-based limit order book model (2022)
  26. Deep learning (2016)
  27. Limit order books (2013)
  28. Optimal market making (2017)
  29. Deep reinforcement learning for market making in corporate bonds: beating the curse of dimensionality (2019)
  30. Spectra of some self-exciting and mutually exciting point processes (1971)
  31. Reinforcement learning with deep energy-based policies (2017)
  32. Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor (2018)
  33. A cluster process representation of a self-exciting process (1974)
  34. Quantitative and comparative analyses of limit order books with general compound Hawkes processes (2019)
  35. Long Short-term Memory (1997)
  36. A dynamic limit order market with fast and slow traders (2014)
  37. Market Making at the Touch with Short-Term Alpha (Chap 10.4.2) (2019)
  38. Limit Order Book Simulations: A Review — → 2402.17359
  39. Stochastic differential equations (1992)
  40. Deep Hawkes process for high-frequency market making (2024)
  41. Algorithmic and High-Frequency Trading Problems for Semi- Markov and Hawkes Jump-Diffusion Models — → 2409.12776
  42. Market Simulation under Adverse Selection — → 2409.12721
  43. Reinforcement Learning in Non-Markov Market-Making — → 2410.14504
  44. Market making under a weakly consistent limit order book model (2019)
  45. Simulation of nonhomogeneous Poisson processes by thinning (1979)
  46. Deep robust reinforcement learning for practical algorithmic trading (2019)
  47. Multivariate hawkes processes (2009)
  48. LOBSTER: Limit Order Book Reconstruction and Visualization (2025) — link
  49. Fill Probabilities in a Limit Order Book with State-Dependent Stochastic Order Flows — → 2403.02572
  50. High-dimensional Hawkes processes for limit order books: modelling, empirical analysis and numerical calibration (2018)
  51. A deep learning approach to estimating fill probabilities in a limit order book (2022)
  52. Forecasting jump arrivals in stock prices: new attention-based network architecture using limit order book data (2019)
  53. The neural hawkes process: A neurally self-modulating multivariate point process (2017)
  54. Lifetime portfolio selection under uncertainty: The continuous-time case (1969)
  55. Option pricing when underlying stock returns are discontinuous (1976)
  56. Human-level control through deep reinforcement learning (2015)
  57. Using full Limit Order Book for price jump prediction (2020)
  58. Optimal consumption and portfolio with both fixed and proportional transaction costs (2002)
  59. Continuous-time stochastic control and optimization with financial applications (2009)
  60. Deep reinforcement learning in quantitative algorithmic trading: A review (2021) — link
  61. Sequence level training with recurrent neural networks (2015) — link
  62. On stochastic optimal control and reinforcement learning by approximate inference (2013)
  63. Optimal Liquidation, Acquisition and Market Making Problems in HFT under Hawkes Models for LOB (2022)
  64. Stochastic Optimal Control Problems in LOB for Various Stochastic Models (2023)
  65. Deep reinforcement learning in cryptocurrency market making (2019) — link
  66. Extending deep reinforcement learning frameworks in cryptocurrency market making (2020) — link
  67. LOB modeling using Hawkes processes with a state-dependent factor (2021) — link
  68. State dependent parallel neural Hawkes process for limit order book event stream prediction and simulation (2022)
  69. Mastering the game of Go with deep neural networks and tree search (2016)
  70. How are reinforcement learning and deep learning algorithms used for big data based decision making in financial industries–A review and research agenda (2022)
  71. General Compound Hawkes Processes for Mid-Price Prediction (2021) — link
  72. 79+ amazing algorithmic trading statistics (2016) — link
  73. Stable Baselines3 (2020) — link
  74. A semi- Markovian modeling of limit order markets (2017)
  75. General semi- Markov model for limit order books (2017)
  76. General compound Hawkes processes in limit order books (2020)
  77. Compound Hawkes processes in limit order books (2019)
  78. Financial modelling with jump processes (2003)
  79. An application of deep reinforcement learning to algorithmic trading (2021)
  80. Robot trajectory optimization using approximate inference (2009)
  81. Optimal investment-consumption models with constraints (1989)
  82. Statistical Analysis of the Price Jumps of Financial Assets Based on LOB Data (2017)
  83. Deep reinforcement learning for trading (2019) — link
  84. Deeplob: Deep convolutional neural networks for limit order books (2019)
  85. Maximum entropy inverse reinforcement learning. (2008)

6 of 93 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2518 linked papers.