# Deep Learning modeling of Limit Order Book: a comparative perspective

arXiv: https://arxiv.org/abs/2007.07319 · HTML: https://mlsanity.com/paper/2007.07319/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Jul 2020.

## Built on by (most cited first, 11 of 11)

- [Deep Reinforcement Learning for Active High Frequency Trading](https://mlsanity.com/paper/2101.07107/) (2021)
- [Multi-Horizon Forecasting for Limit Order Books: Novel Deep Learning Approaches and Hardware Acceleration using Intelligent Processing Units](https://mlsanity.com/paper/2105.10430/) (2021)
- [From Deep Learning to LLMs: A survey of AI in Quantitative Investment](https://mlsanity.com/paper/2503.21422/) (2025)
- [Deep Learning for Market by Order Data](https://mlsanity.com/paper/2102.08811/) (2021)
- [HLOB -- Information Persistence and Structure in Limit Order Books](https://mlsanity.com/paper/2405.18938/) (2024)
- [Deep Limit Order Book Forecasting](https://mlsanity.com/paper/2403.09267/) (2024)
- [Sparsification and Filtering for Spatial-temporal GNN in Multivariate Time-series](https://mlsanity.com/paper/2203.03991/) (2022)
- [Deep Reinforcement Learning for Market Making Under a Hawkes Process-Based Limit Order Book Model](https://mlsanity.com/paper/2207.09951/) (2022)
- [Accelerating Machine Learning Training Time for Limit Order Book Prediction](https://mlsanity.com/paper/2206.09041/) (2022)
- [Exploring Microstructural Dynamics in Cryptocurrency Limit Order Books: Better Inputs Matter More Than Stacking Another Hidden Layer](https://mlsanity.com/paper/2506.05764/) (2025)
- [An `Inverse' Experimental Framework to Estimate Market Efficiency](https://mlsanity.com/paper/2604.18130/) (2026)

## Abstract (arXiv)

The present work addresses theoretical and practical questions in the domain of Deep Learning for High Frequency Trading. State-of-the-art models such as Random models, Logistic Regressions, LSTMs, LSTMs equipped with an Attention mask, CNN-LSTMs and MLPs are reviewed and compared on the same tasks, feature space and dataset, and then clustered according to pairwise similarity and performance metrics. The underlying dimensions of the modeling techniques are hence investigated to understand whether these are intrinsic to the Limit Order Book's dynamics. We observe that the Multilayer Perceptron performs comparably to or better than state-of-the-art CNN-LSTM architectures indicating that dynamic spatial and temporal dimensions are a good approximation of the LOB's dynamics, but not necessarily the true underlying dimensions.