Download this Paper Open PDF in Browser

Implementing Deep Neural Networks for Financial Market Prediction on the Intel Xeon Phi

6 Pages Posted: 7 Jul 2015 Last revised: 13 Sep 2015

Matthew Francis Dixon

Illinois Institute of Technology - Stuart School of Business, IIT

Diego Klabjan

Northwestern University

Jin Hoon Bang

Northwestern University

Date Written: July 6, 2015

Abstract

Deep neural networks (DNNs) are powerful types of artificial neural networks (ANNs) that use several hidden layers. They have recently gained considerable attention in the speech transcription and image recognition community (Krizhevsky et al., 2012) for their superior predictive properties including robustness to overfitting. However their application to financial market prediction has not been previously researched, partly because of their computational complexity. This paper describes the application of DNNs to predicting financial market movement directions. A critical step in the viability of the approach in practice is the ability to effectively deploy the algorithm on general purpose high performance computing infrastructure. Using an Intel Xeon Phi co-processor with 61 cores, we describe the process for efficient implementation of the batched stochastic gradient descent algorithm and demonstrate a 11.4x speedup on the Intel Xeon Phi over a serial implementation on the Intel Xeon.

Keywords: machine learning, financial markets, many-core computing

Suggested Citation

Dixon, Matthew Francis and Klabjan, Diego and Bang, Jin Hoon, Implementing Deep Neural Networks for Financial Market Prediction on the Intel Xeon Phi (July 6, 2015). Available at SSRN: https://ssrn.com/abstract=2627258 or http://dx.doi.org/10.2139/ssrn.2627258

Matthew Francis Dixon (Contact Author)

Illinois Institute of Technology - Stuart School of Business, IIT ( email )

10 West 35th Street, 18th Floor
Chicago, IL 60616
United States

Diego Klabjan

Northwestern University ( email )

2001 Sheridan Road
Evanston, IL 60208
United States

Jin Hoon Bang

Northwestern University ( email )

2001 Sheridan Road
Evanston, IL 60208
United States

Paper statistics

Downloads
1,244
Rank
12,534
Abstract Views
3,155