DiffVolume: Diffusion Models for Volume Generation in Limit Order Books

TL;DR

DiffVolume is a diffusion-based model that generates realistic, controllable limit order book volume snapshots, improving statistical realism and aiding liquidity prediction tasks.

Contribution

The paper introduces DiffVolume, a novel diffusion model for generating high-dimensional LOB volume data with controllable features and improved realism over prior GAN-based approaches.

Findings

DiffVolume outperforms GANs in reproducing statistical properties of LOB volumes.

Counterfactual generation enables scenario analysis of liquidity conditions.

Synthetic data from DiffVolume enhances liquidity forecasting accuracy.

Abstract

Modeling limit order books (LOBs) dynamics is a fundamental problem in market microstructure research. In particular, generating high-dimensional volume snapshots with strong temporal and liquidity-dependent patterns remains a challenging task, despite recent work exploring the application of Generative Adversarial Networks to LOBs. In this work, we propose a conditional \textbf{Diff}usion model for the generation of future LOB \textbf{Volume} snapshots (\textbf{DiffVolume}). We evaluate our model across three axes: (1) \textit{Realism}, where we show that DiffVolume, conditioned on past volume history and time of day, better reproduces statistical properties such as marginal distribution, spatial correlation, and autocorrelation decay; (2) \textit{Counterfactual generation}, allowing for controllable generation under hypothetical liquidity scenarios by additionally conditioning on a target future liquidity profile; and (3) \textit{Downstream prediction}, where we show that the synthetic counterfactual data from our model improves the performance of future liquidity forecasting models. Together, these results suggest that DiffVolume provides a powerful and flexible framework for realistic and controllable LOB volume generation.