DSLOB: A Synthetic Limit Order Book Dataset for Benchmarking Forecasting Algorithms under Distributional Shift

TL;DR

This paper introduces DSLOB, a synthetic limit order book dataset designed to benchmark forecasting algorithms under distributional shifts, facilitating research on model robustness in unseen market scenarios.

Contribution

The paper presents a novel synthetic LOB dataset with labeled out-of-distribution samples, enabling controlled benchmarking of forecasting models under distributional shifts.

Findings

Forecasting performance varies significantly under distributional shifts.

Current models need improved robustness to out-of-distribution data.

Synthetic dataset helps identify model weaknesses in stressed market conditions.

Abstract

In electronic trading markets, limit order books (LOBs) provide information about pending buy/sell orders at various price levels for a given security. Recently, there has been a growing interest in using LOB data for resolving downstream machine learning tasks (e.g., forecasting). However, dealing with out-of-distribution (OOD) LOB data is challenging since distributional shifts are unlabeled in current publicly available LOB datasets. Therefore, it is critical to build a synthetic LOB dataset with labeled OOD samples serving as a testbed for developing models that generalize well to unseen scenarios. In this work, we utilize a multi-agent market simulator to build a synthetic LOB dataset, named DSLOB, with and without market stress scenarios, which allows for the design of controlled distributional shift benchmarking. Using the proposed synthetic dataset, we provide a holistic analysis on the forecasting performance of three different state-of-the-art forecasting methods. Our results reflect the need for increased researcher efforts to develop algorithms with robustness to distributional shifts in high-frequency time series data.