Deep Learning for Market by Order Data

Abstract

Market by order (MBO) data -a detailed feed of individual trade instructions for a given stock on an exchange -is arguably one of the most granular sources of microstructure information. While limit order books (LOBs) are implicitly derived from it, MBO data is largely neglected by current academic literature which focuses primarily on LOB modelling. In this paper, we demonstrate the utility of MBO data for forecasting high-frequency price movements, providing an orthogonal source of information to LOB snapshots. We provide the first predictive analysis on MBO data by carefully introducing the data structure and presenting a specific normalisation scheme to consider level information in order books and to allow model training with multiple instruments. Through forecasting experiments using deep neural networks, we show that while MBO-driven and LOB-driven models individually provide similar performance, ensembles of the two can lead to improvements in forecasting accuracy -indicating that MBO data is additive to LOB-based features.

Predicting Stock Price Changes Based on the Limit Order Book: A Survey

“…• Use more recent LOB data for the input features; • Do not implicitly assume the mid-price execution; • To properly train the deep learning models, an extensive dataset should be used, otherwise the over-fitting problem could become severe; • Careful pre-processing of the dataset should be performed as required to filter out erroneous data; • Data for different stocks should be distinguishable in the dataset; • It is advocated by a number of authors in recent studies [56,62] that Order Flow in addition to the LOB data can slightly improve the performance of the stock price prediction models.…”

Multi-Horizon Forecasting for Limit Order Books: Novel Deep Learning Approaches and Hardware Acceleration using Intelligent Processing Units

“…Literature ReviewDeep learning models have been heavily used for prediction tasks on LOB data, whereTsantekidis et al (2017a,b);Sirignano and Cont (2019);Zhang et al (2019a) helped to build the foundation in this area. Subsequently, a wide range of extensions have been proposed to improve predictive performance, including Bayesian deep networks(Zhang et al, 2018), Quantile regression(Zhang et al, 2019b), Transformers(Wallbridge, 2020) and usages of more granular market by order data(Zhang et al, 2021). In addition, LOB data has been studied in the context of reinforcement learning(Wei et al, 2019), market-making (Sadighian, 2019), cryptocurries(Jha et al, 2020) and portfolio optimisation(Sangadiev et al, 2020).…”