Paper: arXiv 2402.17359

Abstract

Limit Order Books (LOBs) serve as a mechanism for buyers and sellers to interact with each other in the financial markets. Modelling and simulating LOBs is quite often necessary for calibrating and fine-tuning the automated trading strategies developed in algorithmic trading research. The recent AI revolution and availability of faster and cheaper compute power has enabled the modelling and simulations to grow richer and even use modern AI techniques. In this review we examine the various kinds of LOB simulation models present in the current state of the art. We provide a classification of the models on the basis of their methodology and provide an aggregate view of the popular stylized facts used in the literature to test the models. We additionally provide a focused study of price impact’s presence in the models since it is one of the more crucial phenomena to model in algorithmic trading. Finally, we conduct a comparative analysis of various qualities of fits of these models and how they perform when tested against empirical data.

Complexity vs Empirical Score

  • Math Complexity: 7.5/10
  • Empirical Rigor: 7.0/10
  • Quadrant: Holy Grail — high math complexity, high empirical rigor

Why this score: The paper involves advanced mathematical modeling of limit order books using stochastic processes and differential equations, placing it in the high math range. Its empirical rigor is high because it reviews simulation models tested against real data, discusses backtesting applications, and evaluates stylized facts, making it data- and implementation-heavy.

Research Flowchart

  flowchart TD
  A["Research Goal<br>Review & Classify<br>LOB Simulation Models"] --> B["Data Collection<br>Stylized Facts &<br>Empirical LOB Data"]
  B --> C["Methodology Classification<br>Agent-Based vs<br>Stochastic vs AI-Driven"]
  C --> D["Simulation & Analysis<br>Model Calibration &<br>Price Impact Study"]
  D --> E{"Model Validation<br>vs Empirical Data"}
  E -->|Fits Stylized Facts| F["Key Findings: Model Performance<br>Comparative Fit Quality<br>Price Impact Accuracy"]
  E -->|Fails Validation| C

Cited References (99)

  1. A Stochastic Model for Order Book Dynamics (2010)
  2. Statistical theory of the continuous double auction (2003) — link
  3. The predictive power of zero intelligence in financial markets (2005) — link
  4. Statistical properties of stock order books: empirical results and models (2002) — link
  5. Limit order books (2013) — link
  6. The Price Impact of Order Book Events (2013) — link
  7. Price Dynamics in a Markovian Limit Order Market (2013) — link
  8. DeepLOB : Deep Convolutional Neural Networks for Limit Order Books (2019) — link
and 91 more
  1. Quant GANs : deep generation of financial time series (2020) — link
  2. Universal features of price formation in financial markets: perspectives from Deep Learning (2018) — link
  3. A steady-state model of the continuous double auction (2003) — link
  4. Statistical Modeling of High-Frequency Financial Data (2011) — link
  5. Simulating and Analyzing Order Book Data: The Queue-Reactive Model (2015)
  6. Modelling high-frequency limit order book dynamics with support vector machines (2015) — link
  7. Modeling financial time-series with generative adversarial networks (2019) — link
  8. A Mathematical Approach to Order Book Modelling (2011) — link
  9. An agent based model of the E-Mini S&P 500 applied to flash crash analysis (2012) — link
  10. Order book dynamics in liquid markets: limit theorems and diffusion approximations (2011) — link
  11. Sig-Wasserstein GANs for Time Series Generation (2022) — link
  12. Hawkes Processes in Finance (2015) — link
  13. Ergodicity and scaling limit of a constrained multivariate Hawkes process (2014) — link
  14. Estimation of slowly decreasing hawkes kernels: application to high-frequency order book dynamics (2016)
  15. " Market making" behaviour in an order book model and its impact on the bid-ask spread (2010) — link
  16. Measuring the resiliency of an electronic limit order book (2007) — link
  17. Long-Time Behavior of a Hawkes Process–Based Limit Order Book (2015) — link
  18. A buffer Hawkes process for limit order books (2017) — link
  19. High-dimensional Hawkes processes for limit order books: modelling, empirical analysis and numerical calibration (2018) — link
  20. From asymptotic properties of general point processes to the ranking of financial agents (2019) — link
  21. A scaling limit for limit order books driven by Hawkes processes (2019)
  22. Hawkes processes and their applications to finance: a review (2018) — link
  23. Deep Hawkes process for high-frequency market making (2021) — link
  24. Abides: Towards high-fidelity market simulation for ai research (2019) — link
  25. Generating Realistic Stock Market Order Streams (2020) — link
  26. High frequency asymptotics for the limit order book (2016)
  27. State-dependent Hawkes processes and their application to limit order book modelling (2022)
  28. A law of large numbers for limit order books (2017)
  29. Modeling high-frequency order flow imbalance by functional limit theorems for two-sided risk processes (2015)
  30. A weak law of large numbers for a limit order book model with fully state dependent order dynamics (2017)
  31. Hydrodynamic limit of order-book dynamics (2018)
  32. A Markov model of a limit order book: thresholds, recurrence, and trading strategies (2018)
  33. Ergodicity and diffusivity of Markovian order book models: a general framework (2017)
  34. Deep learning modeling of limit order book: A comparative perspective (2020) — link
  35. Estimation of an Order Book Dependent Hawkes Process for Large Datasets — → 2307.09077
  36. A one-level limit order book model with memory and variable spread (2017)
  37. Algorithmic trading with Markov chains (2010)
  38. Limit order books, diffusion approximations and reflected SPDEs: from microscopic to macroscopic models (2020)
  39. Second order approximations for limit order books (2018)
  40. Second-Order Approximation of Limit Order Books in a Single-Scale Regime — → 2308.00805
  41. Order-book modeling and market making strategies (2018)
  42. Modeling Bid and Ask Price Dynamics with an Extended Hawkes Process and Its Empirical Applications for High-Frequency Stock Market Data (2022)
  43. Hawkes-based models for high frequency financial data (2022)
  44. A stochastic partial differential equation model for limit order book dynamics (2021)
  45. Dynamic equilibrium limit order book model and optimal execution problem (2014) — link
  46. Equilibrium Model of Limit Order Books: A Mean-Field Game View (2022)
  47. Order book dynamics with liquidity fluctuations: limit theorems and large deviations (2020) — link
  48. Dynamic calibration of order flow models with generative adversarial networks (2022)
  49. Limit Order Book Simulation with Generative Adversarial Networks (2023)
  50. Intra-Day Price Simulation with Generative Adversarial Modelling of the Order Flow (2021)
  51. Generative adversarial nets (2014)
  52. Conditional generative adversarial nets (2014) — link
  53. Wasserstein generative adversarial networks (2017)
  54. The price impact of order book events (2014)
  55. Price discovery and learning during the preopening period in the Paris Bourse (1999)
  56. Limit order book as a market for liquidity (2005)
  57. The lob recreation model: Predicting the limit order book from taq history using an ordinary differential equation recurrent neural network (2021)
  58. The Limit Order Book Recreation Model (LOBRM): An Extended Analysis (2021)
  59. State Dependent Parallel Neural Hawkes Process for Limit Order Book Event Stream Prediction and Simulation (2022)
  60. Neural Stochastic Agent-Based Limit Order Book Simulation: A Hybrid Methodology — → 2303.00080
  61. Fast agent-based simulation framework of limit order books with applications to pro-rata markets and the study of latency effects (2020) — link
  62. Deep learning for market by order data (2021)
  63. Generative AI for End-to-End Limit Order Book Modelling: A Token-Level Autoregressive Generative Model of Message Flow Using a Deep State Space Network — → 2309.00638
  64. Marked Hawkes process modeling of price dynamics and volatility estimation (2017)
  65. The neural hawkes process: A neurally self-modulating multivariate point process (2017)
  66. Deep Learning (2016)
  67. Machine Learning and Data Sciences for Financial Markets: A Guide to Contemporary Practices (2023)
  68. Probability distribution of returns in the Heston model with stochastic volatility* (2002) — link
  69. Learning to simulate realistic limit order book markets from data as a World Agent (2022)
  70. Conditional Generators for Limit Order Book Environments: Explainability, Challenges, and Robustness — → 2306.12806
  71. Limit Order Books (2016)
  72. Hawkes Process: Fast Calibration, Application to Trade Clustering, and Diffusive Limit (2014) — link
  73. Hawkes model specification for limit order books (2022)
  74. High-frequency simulations of an order book: a two-scale approach (2011)
  75. Econophysics review: II. Agent-based models (2011)
  76. Get real: Realism metrics for robust limit order book market simulations (2020)
  77. The probability of backtest overfitting (2016)
  78. Pseudomathematics and financial charlatanism: The effects of backtest over fitting on out-of-sample performance (2014)
  79. A data-driven market simulator for small data environments (2020) — link
  80. An estimation procedure for the Hawkes process (2017)
  81. Queue-reactive Hawkes models for the order flow (2019) — link
  82. The role of volume in order book dynamics: a multivariate Hawkes process analysis (2017)
  83. Tick: a Python library for statistical learning, with a particular emphasis on time-dependent modelling (2017) — link
  84. Market impacts and the life cycle of investors orders (2015)
  85. Order Flow and Price Formation (2023)
  86. Deciphering How Investors’ Daily Flows are Forming Prices (2023)
  87. Data-snooping, technical trading rule performance, and the bootstrap (1999)
  88. A reality check for data snooping (2000)
  89. Analysis and modeling of client order flow in limit order markets (2023)
  90. A mathematical framework for modelling order book dynamics — → 2302.01169
  91. JAX-LOB: A GPU-Accelerated limit order book simulator to unlock large scale reinforcement learning for trading (2023) — link

6 of 99 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2518 linked papers.