Research on Prediction Model of Stock Price Based on LM-BP Neural Network

DOI

10.2991/lemcs-14.2014.177How to use a DOI?

Keywords

LM-BP neural network; stock price; prediction

Abstract

LM (Levenberg-Marquardt) algorithm is an optimization algorithm for the overall situation which is appropriate for neural network training. It is assumed that standard BP neural network tends to reach the local minimum instead of the optimization of the whole, demand much more training resulting in the low learning efficiency and low rate of convergence. At the same time, it seems easily to forget former sample. To solve the above disadvantages, this paper intends to form prediction model of stock price based on LM- BP neural network to forecast stock price, as well as compared with the prediction result carried out by standard BP neural network. At the end, this paper achieves the satisfactory result.

Copyright

© 2014, 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  - Feng Li
PY  - 2014/05
DA  - 2014/05
TI  - Research on Prediction Model of Stock Price Based on LM-BP Neural Network
BT  - Proceedings of the International Conference on Logistics, Engineering, Management and Computer Science
PB  - Atlantis Press
SP  - 776
EP  - 778
SN  - 1951-6851
UR  - https://doi.org/10.2991/lemcs-14.2014.177
DO  - 10.2991/lemcs-14.2014.177
ID  - Li2014/05
ER  -