# Exploring Microstructural Dynamics in Cryptocurrency Limit Order Books: Better Inputs Matter More Than Stacking Another Hidden Layer

arXiv: https://arxiv.org/abs/2506.05764 · HTML: https://mlsanity.com/paper/2506.05764/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 24 references that are in the map.
- First posted on arXiv 6 Jun 2025.

## Builds on (most cited first, 8 of 8)

- [Universal features of price formation in financial markets: perspectives from Deep Learning](https://mlsanity.com/paper/1803.06917/) (2018)
- [Benchmark Dataset for Mid-Price Forecasting of Limit Order Book Data with Machine Learning Methods](https://mlsanity.com/paper/1705.03233/) (2017)
- [Using Deep Learning for price prediction by exploiting stationary limit order book features](https://mlsanity.com/paper/1810.09965/) (2018)
- [Deep Learning modeling of Limit Order Book: a comparative perspective](https://mlsanity.com/paper/2007.07319/) (2020)
- [Deep Limit Order Book Forecasting](https://mlsanity.com/paper/2403.09267/) (2024)
- [How Robust are Limit Order Book Representations under Data Perturbation?](https://mlsanity.com/paper/2110.04752/) (2021)
- [Axial-LOB: High-Frequency Trading with Axial Attention](https://mlsanity.com/paper/2212.01807/) (2022)
- [TLOB: A Novel Transformer Model with Dual Attention for Price Trend Prediction with Limit Order Book Data](https://mlsanity.com/paper/2502.15757/) (2025)

## Abstract (arXiv)

Cryptocurrency price dynamics are driven largely by microstructural supply demand imbalances in the limit order book (LOB), yet the highly noisy nature of LOB data complicates the signal extraction process. Prior research has demonstrated that deep-learning architectures can yield promising predictive performance on pre-processed equity and futures LOB data, but they often treat model complexity as an unqualified virtue. In this paper, we aim to examine whether adding extra hidden layers or parameters to "blackbox ish" neural networks genuinely enhances short term price forecasting, or if gains are primarily attributable to data preprocessing and feature engineering. We benchmark a spectrum of models from interpretable baselines, logistic regression, XGBoost to deep architectures (DeepLOB, Conv1D+LSTM) on BTC/USDT LOB snapshots sampled at 100 ms to multi second intervals using publicly available Bybit data. We introduce two data filtering pipelines (Kalman, Savitzky Golay) and evaluate both binary (up/down) and ternary (up/flat/down) labeling schemes. Our analysis compares models on out of sample accuracy, latency, and robustness to noise. Results reveal that, with data preprocessing and hyperparameter tuning, simpler models can match and even exceed the performance of more complex networks, offering faster inference and greater interpretability.