Performance Analysis of Sequential and Parallel Neural Network Algorithm for Stock Price Forecasting

View Sample PDF

Author(s): Rashedur M. Rahman (North South University, Bangladesh), Ruppa K. Thulasiram (University of Manitoba, Canada)and Parimala Thulasiraman (University of Manitoba, Canada)
Copyright: 2013
Pages: 25
Source title: Applications and Developments in Grid, Cloud, and High Performance Computing
Source Author(s)/Editor(s): Emmanuel Udoh (Sullivan University, USA)
DOI: 10.4018/978-1-4666-2065-0.ch007

Keywords: Computer Science & IT / Grid & High Performance Computing / High Performance Computing / Information Science Reference

Purchase

View Performance Analysis of Sequential and Parallel Neural Network Algorithm for Stock Price Forecasting on the publisher's website for pricing and purchasing information.

Abstract

The neural network is popular and used in many areas within the financial field, such as credit authorization screenings, regularities in security price movements, simulations of market behaviour, and so forth. In this research, the authors use a neural network technique for stock price forecasting of Great West Life, an insurance company based in Winnipeg, Canada. The Backpropagation algorithm is a popular algorithm to train a neural network. However, one drawback of traditional Backpropagation algorithm is that it takes a substantial amount of training time. To expedite the training process, the authors design and develop different parallel and multithreaded neural network algorithms. The authors implement parallel neural network algorithms on both shared memory architecture using OpenMP and distributed memory architecture using MPI and analyze the performance of those algorithms. They also compare the results with traditional auto-regression model to establish accuracy.

The IRMA Community

Research IRM

Performance Analysis of Sequential and Parallel Neural Network Algorithm for Stock Price Forecasting

Purchase

Abstract

Related Content

IRMA Sponsors