Investigating the size and value effect in determining performance of Australian listed companies: A neural network approach

Publication Type:
Conference Proceeding
Conferences in Research and Practice in Information Technology Series, 2006, 61 pp. 155 - 161
Issue Date:
Full metadata record
Files in This Item:
Filename Description Size
Thumbnail2006005682.pdf348.6 kB
Adobe PDF
This paper explores the size and value effect in influencing performance of individual companies using backpropagation neural networks. According to existing theory, companies with small market capitalization and high book to market ratios have a tendency to perform better in the future. Data from over 300 Australian Stock Exchange listed companies between 2000-2004 is examined and a neural network is trained to predict company performance based on market capitalization, book to market ratio, beta and standard deviation. Evidence for the value effect was found over longer time periods but there was less for the size effect. Poor company performance was also observed to be correlated with high risk. © 2006, Australian Computer Society, Inc.
Please use this identifier to cite or link to this item: