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

Author

Jan, Tony ; Yu, Ting ; Debenham, John ; Simoff, Simeon

Author_Institution

Fac. of Inf. Technol., Univ. of Technol., Sydney, NSW, Australia

fYear

2004

fDate

14-16 July 2004

Firstpage

81

Lastpage

84

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 quantization 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

finance; learning (artificial intelligence); multilayer perceptrons; prediction theory; probability; radial basis function networks; vector quantisation; embedded local linear models; financial prediction; model complexity; neural network; piecewise linear model; probabilistic learning network; semiparametric model; vector quantization; Australia; Covariance matrix; Electronic mail; Information technology; Kernel; Mathematical model; Neural networks; Piecewise linear techniques; Predictive models; Smoothing methods;

fLanguage

English

Publisher

ieee

Conference_Titel

Computational Intelligence for Measurement Systems and Applications, 2004. CIMSA. 2004 IEEE International Conference on

Print_ISBN

0-7803-8341-9

Type

conf

DOI

10.1109/CIMSA.2004.1397236

Filename

1397236