A hybrid mining model based on neural network and kernel smoothing technique

Authors:
Defu Zhang;Qingshan Jiang;Xin Li
Affiliations:
Department of Computer Science, Xiamen University, China;Department of Computer Science, Xiamen University, China;Department of Computer Science, Xiamen University, China
Venue:
ICCS'05 Proceedings of the 5th international conference on Computational Science - Volume Part III
Year:
2005

Citing 8
Cited 0

Introduction to the theory of neural computation

Introduction to the theory of neural computation
Neural networks: applications in industry, business and science

Communications of the ACM
Stock performance modeling using neural networks: a comparative study with regression models

Neural Networks
Neural networks in business: techniques and applications for the operations researcher

Computers and Operations Research - Neural networks in business
Evolving artificial neural networks to combine financial forecasts

IEEE Transactions on Evolutionary Computation
Comparative study of stock trend prediction using time delay, recurrent and probabilistic neural networks

IEEE Transactions on Neural Networks
Introduction to the special issue on neural networks in financial engineering

IEEE Transactions on Neural Networks
Data mining in soft computing framework: a survey

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

Neural networks as data mining tools are becoming increasingly popular in business. In this paper, a hybrid mining model based on neural network and kernel smoothing technique is developed. The kernel smoothing technique is used to preprocess data and help decision-making. Neural network is employed to predict the long trends of stock price. In addition, some trading rules involving trading decision-making are considered. The China Shanghai Composite Index is as case study. The return achieved by the hybrid mining model is four times as large as that achieved by the buy and hold strategy, so the proposed model is promising and certainly warrants further research.