Predicting Jump Arrivals in Stock Prices Using Neural Networks with Limit Order Book Data

27 Pages Posted: 24 Apr 2018 Last revised: 1 May 2018

See all articles by Milla Mäkinen

Milla Mäkinen

Tampere University of Technology

Alexandros Iosifidis

Aarhus University

Moncef Gabbouj

Tampere University of Technology

Juho Kanniainen

Tampere University

Date Written: April 19, 2018

Abstract

This paper proposes a new method for predicting jump arrivals in stock markets with high-frequency limit order book data. We introduce a new model architecture, based on Convolutional Long Short-Term Memory with attention, to apply time series representation learning with memory and to focus the prediction attention on the most important features to improve performance. Using order book data on five liquid U.S. stocks, we provide empirical evidence on the efficacy of the proposed approach. We find that the proposed approach with an attention mechanism outperforms the multi-layer perceptron network as well as the convolutional neural network and Long Short-Term memory model. The use of limit order book data was found to improve the performance of the proposed model in jump prediction, either clearly or marginally, depending on the underlying stock.

Keywords: Limit Order Book Data, Neural Networks, Convolutional Networks, Long Short-Term Memory, Attention Mechanism

Suggested Citation

Mäkinen, Milla and Iosifidis, Alexandros and Gabbouj, Moncef and Kanniainen, Juho, Predicting Jump Arrivals in Stock Prices Using Neural Networks with Limit Order Book Data (April 19, 2018). Available at SSRN: https://ssrn.com/abstract=3165408 or http://dx.doi.org/10.2139/ssrn.3165408

Milla Mäkinen (Contact Author)

Tampere University of Technology ( email )

P.O. 541, Korkeakoulunkatu 8 (Festia building)
Tampere, FI-33101
Finland

Moncef Gabbouj

Tampere University of Technology ( email )

P.O. 541, Korkeakoulunkatu 8 (Festia building)
Tampere, FI-33101
Finland

HOME PAGE: http://www.cs.tut.fi/~moncef

Juho Kanniainen

Tampere University ( email )

P.O. 541, Korkeakoulunkatu 8 (Festia building)
Tampere, FI-33101
Finland

HOME PAGE: http://https://sites.google.com/site/juhokanniainen/

Register to save articles to
your library

Register

Paper statistics

Downloads
195
Abstract Views
638
rank
153,576
PlumX Metrics