Stock Price Prediction Model Based on IWO Neural Network and its Applications

Abstract:

In view of the deficiency of the standard back-propagation algorithm based on steepest descent method, a new kind of optimization strategy called invasive weed optimization (IWO) algorithm is introduced into the training process of feed-forward neural networks, and then a prediction model based on IWO feed-forward neural network (IWO-NN) is given. By the dynamic adjustment of standard deviation of the distribution of offspring individuals in IWO, the local convergence speed of networks is improved and the defect of trapping into a local optimum is reduced. By the empirical study of stock price prediction in Sany Heavy Industry, the results show that this method has better global astringency, robustness, and it is insensitive to initial values.

• Periodical: Advanced Materials Research (Volumes 989-994)
• Pages: 1635-1640
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.989-994.1635
• Online since: July 2014
• Authors: Hong Liu*, Xiao Yan Lv
• Keywords: Feed-Forward Neural Network, Invasive Weed Optimization, Stock Price Prediction

References

[1] Lv Gang, Chen Xiaoping, Zhao Heming, An IA-BP Hybird Algorithm to Optimize Multilayer Feed-forward Neural Networks [J]. Computer Engineering and Applications, 2003: 39(27): 27-28.

[2] Wang Jianqun, Lu Zhihua, Three-layer Feed Forward Artificial Neural Network Global Optimum Approach [J]. Mathematics in Practice and Theory, 2003, 33(7): 1-8.

[3] MEHRABIAN A R, LUCAS C. A novel numerical optimization algorithm inspired from weed colonization [J]. Ecological Informatics, 2006, 1(4): 355-366.

DOI: 10.1016/j.ecoinf.2006.07.003

[4] Wang Jing, The Optimization of Feed- Forward Neural Networks Based on Ant Colony Algorithm[J]. Computer Engineering and Applications, 2006(25): 54-55.

[5] Fei Liangjun. Computational Intelligence Approach for Discovering the Prediction Model of Financial Market [J]. Journal of Software, 1999. 10(4): 395 -399.

[6] RITWIK GIRI, ARITRA CHOWDHURY, ARNOB GHOSH, etc. A modified invasive weed optimization algorithm for training of feed-forward neural networks[C]. IEEE International Conference on Systems Man and Cvbernetics(SMC). Istanbul: IEEE. 2010: 3166-3173.

DOI: 10.1109/icsmc.2010.5642265