TABL-ABM: A Hybrid Framework for Synthetic LOB Generation

TL;DR

This paper introduces a hybrid framework combining agent-based modeling and deep learning to generate realistic synthetic limit order book data, aiming to improve data fidelity for training trading models.

Contribution

It presents a novel integration of the Chiarella agent-based model with the TABL deep learning model for improved synthetic LOB data generation.

Findings

Generates realistic price dynamics

Captures stylised facts of market behavior

Identifies limitations in microstructure reproduction

Abstract

The recent application of deep learning models to financial trading has heightened the need for high fidelity financial time series data. This synthetic data can be used to supplement historical data to train large trading models. The state-of-the-art models for the generative application often rely on huge amounts of historical data and large, complicated models. These models range from autoregressive and diffusion-based models through to architecturally simpler models such as the temporal-attention bilinear layer. Agent-based approaches to modelling limit order book dynamics can also recreate trading activity through mechanistic models of trader behaviours. In this work, we demonstrate how a popular agent-based framework for simulating intraday trading activity, the Chiarella model, can be combined with one of the most performant deep learning models for forecasting multi-variate time series, the TABL model. This forecasting model is coupled to a simulation of a matching engine with a novel method for simulating deleted order flow. Our simulator gives us the ability to test the generative abilities of the forecasting model using stylised facts. Our results show that this methodology generates realistic price dynamics however, when analysing deeper, parts of the markets microstructure are not accurately recreated, highlighting the necessity for including more sophisticated agent behaviors into the modeling framework to help account for tail events.