偏最小二乘回归的贝叶斯正则化神经网络集成模型在证券分析预测中的应用

神经网络集成技术能有效地提高神经网络的预测精度和泛化能力,已经成为机器学习和神经计算领域的一个研究热点.利用Bagging技术和不同的神经网络算法生成集成个体,并用偏最小二乘回归方法从中提取集成因子,再利用贝叶斯正则化神经网络对其集成,以此建立上证指数预测模型.通过上证指数开、收盘价进行实例分析,计算结果表明该方法预测精度高、稳定性好.

Bayesian Regularization Neural Network Ensemble Model Based on Partial Least Squares Regression and Its Application in Stock Market

Neural Network ensemble can significantly improve the forecasting accuracy and the generalization ability.Recently, neural network becomes a hot topic in machine learning and neural computing application.A novel ensemble algorithm is proposed.Firstly,many individual neural networks are generated by Bagging techniques and different training algorithm.Secondly,The Partial Least Squares Regression is used to select the appropriate ensemble members.Finally,Bayesian Regularization Neural Network method is used for neural network ensemble.This method be established the forecast model of Shanghai Stock Exchange index.The result shows that the ensemble network has reinforcement learning capacities and generalization ability.Ideal results have high accuracy and stability.