Deakin University
Browse

File(s) under permanent embargo

Effectiveness of using quantified intermarket influence for predicting trading signals of stock markets

Version 2 2024-06-05, 03:23
Version 1 2019-07-15, 14:09
journal contribution
posted on 2024-06-05, 03:23 authored by CD Tilakaratne, Musa MammadovMusa Mammadov, S Morris
This paper investigates the use of influence from foreign stock markets (intermarket influence) to predict the trading signals, buy, hold and sell, of the of a given stock market. Australian All Ordinary Index was selected as the stock market whose trading signals to be predicted. Influence is taken into account as a set of input variables for prediction. Two types of input variables were considered: quantified (weighted) input variables and their un-quantified counterparts. Two criteria was applied to determine the trading signals: one is based on the relative returns while the other uses the conditional probability that a given relative return is greater than or equals zero. The prediction of trading signals was done by Feedforward neural networks, Probabilistic neural networks and so called probabilistic approach which was proposed in past studies. Results suggested that using quantified intermarket influence as input variables to predict trading signals, is more effective than using their un-quantified counterparts. © 2007, Australian Computer Society, Inc.

History

Journal

Conferences in Research and Practice in Information Technology

Volume

70

Pagination

167-175

Location

Darlinghurst, N.S.W.

Language

eng

Publication classification

CN.1 Other journal article

Copyright notice

2007, Australian Computer Society

Publisher

Australian Computer Society

Usage metrics

    Research Publications

    Categories

    No categories selected

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC