Isolating Stock Prices Variation with Neural Networks

Book chapter


Draganova, Chrisina, Lanitis, Andreas and Christodoulou, Chris 2009. Isolating Stock Prices Variation with Neural Networks. in: EANN 2009: Engineering Applications of Neural Networks Springer. pp. 401-408
AuthorsDraganova, Chrisina, Lanitis, Andreas and Christodoulou, Chris
Abstract

In this study we aim to define a mapping function that relates the general index value among a set of shares to the prices of individual shares. In more general terms this is problem of defining the relationship between multivariate data distributions and a specific source of variation within these distributions where the source of variation in question represents a quantity of interest related to a particular problem domain. In this respect we aim to learn a complex mapping function that can be used for mapping different values of the quantity of interest to typical novel samples of the distribution. In our investigation we compare the performance of standard neural network based methods like Multilayer Perceptrons (MLPs) and Radial Basis Functions (RBFs) as well as Mixture Density Networks (MDNs) and a latent variable method, the General Topographic Mapping (GTM). As a reference benchmark of the prediction accuracy we consider a simple method based on the average values over certain intervals of the quantity of interest that we are trying to isolate (the so called Sample Average (SA) method). According to the results, MLPs and RBFs outperform MDNs and the GTM for this one-to-many mapping problem.

KeywordsStock Price Prediction; Neural Networks; Multivariate Statistics; One-to-Many Mapping.
Book titleEANN 2009: Engineering Applications of Neural Networks
Page range401-408
Year2009
PublisherSpringer
Publication dates
Print2009
Publication process dates
Deposited22 Feb 2010
Series Communications in Computer and Information Science
EventEngineering Applications of Neural Networks 11th International Conference (EANN 2009)
ISBN978-3-642-03969-0
ISSN1865-0929
1865-0937
Digital Object Identifier (DOI)doi:10.1007/978-3-642-03969-0_37
Web address (URL)http://hdl.handle.net/10552/607
Additional information

Citation:
Draganova, C., Lanitis A., and Christodoulou C. (2009) ‘Isolating Stock Prices Variation with Neural Networks’ In: Engineering Applications of Neural Networks 11th International Conference, EANN 2009, London, UK, August 27-29, 2009, CCIS volume 43, Berlin: Springer pp. 401- 408..

Accepted author manuscript
License
CC BY-ND
Permalink -

https://repository.uel.ac.uk/item/86435

  • 3
    total views
  • 27
    total downloads
  • 1
    views this month
  • 5
    downloads this month