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

TL;DR

This study shows that in cryptocurrency limit order book prediction, data preprocessing and feature engineering are more crucial than increasing model complexity, as simpler models can match or outperform complex neural networks.

Contribution

The paper demonstrates that effective data filtering and hyperparameter tuning enable simpler models to achieve comparable or better performance than complex deep learning architectures in LOB prediction.

Findings

Simpler models can match complex neural networks in accuracy.

Data preprocessing significantly impacts predictive performance.

Preprocessing methods improve robustness and inference speed.

Abstract

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.