Modelling high-frequency limit order book dynamics with support vector machines

By Alec N. Kercheval. 2015

139 citations recorded by the source corpus.

Subfields: Finance, Management Science and Operations Research

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Finance

In Management Science and Operations Research

Citations in the corpus

Using deep learning to detect price change indications in financial markets (2017, methodology): “Given some input features machine learning models can be used to predict the behaviour of various aspects of financial markets [1], [2], [3], [4].”
Sequence classification of the limit order book using recurrent neural networks (2017, methodology): “variables are nonlinear and input space is often high dimensional. A number of researchers have applied machine learning methods to the study of limit order book dynamics (Kearns and Nevmyvaka, 2013; Kercheval and Zhang, 2015; Sirignano, 2016; Dixon et al., 2017). This paper takes an algorithmic app”
Forecasting Stock Prices from the Limit Order Book Using Convolutional Neural Networks (2017, methodology): “An application using high frequency limit order book (LOB) data is [4], where the authors create a set of handcrafted features, such as price differences, bidask spreads, and price and volume derivatives.”
Time-series classification using neural Bag-of-Features (2017, methodology): “For example, each raw (multidimensional) time-series point can be considered as a feature vector [8], short intervals of various lengths can be used to allow for handling time warping [7], or handcrafted features can be extracted from several points of the time-series [12].”
Learning Deep Representations with Probabilistic Knowledge Transfer (2018, background): “, high-frequency trading analysis [23], predicting various properties of chemical compounds [30], etc.”
Deep learning for limit order books (2016, unknown): “Kercheval and Zhang (2015) use support vector machines to model whether a stock’s mid-price increases, decreases, or remains the same; they do not model the actual probabilities of events, instead only predicting whether a particular event will occur.”
Benchmark Dataset for Mid-Price Prediction of Limit Order Book data (2017, methodology): “Han et al. [23] base their research on Kercheval’s and Zhang’s [28] multi-class SVM for mid-price movement prediction.”
A High Frequency Trade Execution Model for Supervised Learning (2017, unknown): “Following Kercheval and Zhang (2015); Sirignano (2016); Dixon (2017), we compose our feature set of ﬁve levels of prices, volumes and number of limit orders on both the ask and bid side of the book.”
DeepLOB: Deep Convolutional Neural Networks for Limit Order Books (2018, methodology): “Note that the FI-2010 dataset is actually downsampled limit order book data because the authors followed [50] to create additional features by using every non-overlapping block of 10 events.”