Financial prediction using modified probabilistic learning network with embedded local linear models

Tony Jan; Ting Yu; John K. Debenham; Simeon J. Simoff

Financial prediction using modified probabilistic learning network with embedded local linear models

Tony Jan, Ting Yu, John K. Debenham, Simeon J. Simoff

School of Computer, Data & Mathematical Sciences

Research output: Chapter in Book / Conference Paper › Conference Paper

Abstract

In this paper, a model is proposed which combines multiple local linear models with a novel modified probabilistic neural network (MPNN). The proposed model is shown to provide improved regularization with reduced computation utilizing semiparametric model approach and efficient vector quantizarion of data space. In this paper, the proposed model is shown to generalize better with reduced variance and model complexity in short-term financial prediction application.

Original language	English
Title of host publication	Proceedings of CIMSA2004: IEEE International Conference on Computational Intelligence for Measurement Systems and Application, held in Boston, Mass., 14-16 July, 2004
Publisher	IEEE
Number of pages	4
ISBN (Print)	0780383419
Publication status	Published - 2004
Event	IEEE International Conference on Computational Intelligence for Measurement Systems and Applications - Duration: 1 Jan 2004 → …

Conference

Conference	IEEE International Conference on Computational Intelligence for Measurement Systems and Applications
Period	1/01/04 → …

Keywords

neural networks (computer science)
linear models (statistics)
finance
artificial intelligence
prediction theory

Cite this

@inproceedings{780b4406dbba49faa4f71fb2e9ba9f4e,

title = "Financial prediction using modified probabilistic learning network with embedded local linear models",

abstract = "In this paper, a model is proposed which combines multiple local linear models with a novel modified probabilistic neural network (MPNN). The proposed model is shown to provide improved regularization with reduced computation utilizing semiparametric model approach and efficient vector quantizarion of data space. In this paper, the proposed model is shown to generalize better with reduced variance and model complexity in short-term financial prediction application.",

keywords = "neural networks (computer science), linear models (statistics), finance, artificial intelligence, prediction theory",

author = "Tony Jan and Ting Yu and Debenham, {John K.} and Simoff, {Simeon J.}",

year = "2004",

language = "English",

isbn = "0780383419",

booktitle = "Proceedings of CIMSA2004: IEEE International Conference on Computational Intelligence for Measurement Systems and Application, held in Boston, Mass., 14-16 July, 2004",

publisher = "IEEE",

note = "IEEE International Conference on Computational Intelligence for Measurement Systems and Applications ; Conference date: 01-01-2004",

}

Jan, T, Yu, T, Debenham, JK & Simoff, SJ 2004, Financial prediction using modified probabilistic learning network with embedded local linear models. in Proceedings of CIMSA2004: IEEE International Conference on Computational Intelligence for Measurement Systems and Application, held in Boston, Mass., 14-16 July, 2004. IEEE, IEEE International Conference on Computational Intelligence for Measurement Systems and Applications, 1/01/04.

Financial prediction using modified probabilistic learning network with embedded local linear models. / Jan, Tony; Yu, Ting; Debenham, John K. et al.
Proceedings of CIMSA2004: IEEE International Conference on Computational Intelligence for Measurement Systems and Application, held in Boston, Mass., 14-16 July, 2004. IEEE, 2004.

Research output: Chapter in Book / Conference Paper › Conference Paper

TY - GEN

T1 - Financial prediction using modified probabilistic learning network with embedded local linear models

AU - Jan, Tony

AU - Yu, Ting

AU - Debenham, John K.

AU - Simoff, Simeon J.

PY - 2004

Y1 - 2004

N2 - In this paper, a model is proposed which combines multiple local linear models with a novel modified probabilistic neural network (MPNN). The proposed model is shown to provide improved regularization with reduced computation utilizing semiparametric model approach and efficient vector quantizarion of data space. In this paper, the proposed model is shown to generalize better with reduced variance and model complexity in short-term financial prediction application.

AB - In this paper, a model is proposed which combines multiple local linear models with a novel modified probabilistic neural network (MPNN). The proposed model is shown to provide improved regularization with reduced computation utilizing semiparametric model approach and efficient vector quantizarion of data space. In this paper, the proposed model is shown to generalize better with reduced variance and model complexity in short-term financial prediction application.

KW - neural networks (computer science)

KW - linear models (statistics)

KW - finance

KW - artificial intelligence

KW - prediction theory

UR - http://handle.uws.edu.au:8081/1959.7/45314

M3 - Conference Paper

SN - 0780383419

BT - Proceedings of CIMSA2004: IEEE International Conference on Computational Intelligence for Measurement Systems and Application, held in Boston, Mass., 14-16 July, 2004

PB - IEEE

T2 - IEEE International Conference on Computational Intelligence for Measurement Systems and Applications

Y2 - 1 January 2004

ER -

Financial prediction using modified probabilistic learning network with embedded local linear models

Abstract

Conference

Keywords

Other files and links

Fingerprint

Cite this