Forecasting closing price indices using neural networks

P. B. Patel, T. Marwala

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

16 Citations (Scopus)

Abstract

Accurate financial prediction is of great practical interest to both individual and institutional investors. This paper proposes an application, which employs artificial neural networks that could be used to assist investors in making financial decisions. The Multi-layer perceptron as well as Radial Basis Function neural network architectures are implemented as classifiers to forecast the closing index price performance. Categorizes that these networks classify are based on a profitable trading strategy that outperforms the long-term "Buy and hold" trading strategy. The Dow Jones Industrial Average, Johannesburg Stock Exchange All Share, Nasdaq 100 and the Nikkei 225 Stock Average indices are considered. The best and worst forecasting classification accuracies obtained were 72% and 64%, respectively. These accuracy levels were attained for the Dow Jones Industrial Average and the Nikkei 225 Stock Average indices, respectively.

Original languageEnglish
Title of host publication2006 IEEE International Conference on Systems, Man and Cybernetics
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages2351-2356
Number of pages6
ISBN (Print)1424401003, 9781424401000
DOIs
Publication statusPublished - 2006
Externally publishedYes
Event2006 IEEE International Conference on Systems, Man and Cybernetics - Taipei, Taiwan, Province of China
Duration: 8 Oct 200611 Oct 2006

Publication series

NameConference Proceedings - IEEE International Conference on Systems, Man and Cybernetics
Volume3
ISSN (Print)1062-922X

Conference

Conference2006 IEEE International Conference on Systems, Man and Cybernetics
Country/TerritoryTaiwan, Province of China
CityTaipei
Period8/10/0611/10/06

ASJC Scopus subject areas

  • General Engineering

Fingerprint

Dive into the research topics of 'Forecasting closing price indices using neural networks'. Together they form a unique fingerprint.

Cite this