Applications of GRNN Based on Particle swarm algorithm Forecasting Stock Prices

DOI

10.2991/icibet.2013.15How to use a DOI?

Abstract

Generalized regression neural network (GRNN) has very good effect on making nonlinear forecasting model with large number of stock data. Particle swarm optimization (PSO) has simple operation analysis and is easy to implement. We use PSO algorithm to optimize the GRNN in order for optimal smoothing factor and connection weights. The prediction errors of the two models are both small. The MSE error by GRNN model reaches 0.0486, while the error by PSO-GRNN model is 0.0104. The analysis shows that PSO-GRNN model is more accurate, more stabilized and more generic than GRNN model.

Copyright

© 2013, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Jinna Lu
AU  - Yanping Bai
PY  - 2013/03
DA  - 2013/03
TI  - Applications of GRNN Based on Particle swarm algorithm Forecasting Stock Prices
BT  - Proceedings of the 2013 International Conference on Information, Business and Education Technology (ICIBET 2013)
PB  - Atlantis Press
SP  - 69
EP  - 72
SN  - 1951-6851
UR  - https://doi.org/10.2991/icibet.2013.15
DO  - 10.2991/icibet.2013.15
ID  - Lu2013/03
ER  -