Title :
Improved RBF Neural Network Ensemble Prediction Model for PMI
Author :
Pan, Leilei ; Li, Xudong
Author_Institution :
Sch. of Math. & Comput., Xihua Univ., Chengdu, China
Abstract :
Final prediction accuracy is greatly influenced by the predictive error of individual RBF network output in the process of RBF Neural Network Ensemble Prediction. The predictive value of individual RBF network model with the help of SAS statistical analysis software is analyzed, and the prediction values that are unreliable are removed out, Therefore the final prediction accuracy is increased. The PMI is predicted based on the improved model and former model, respectively. The results show that the relative prediction error is reduced by about 0.2%.
Keywords :
economic indicators; manufacturing data processing; radial basis function networks; statistical analysis; PMI; RBF neural network ensemble prediction model; SAS statistical analysis software; economic composite index; economic health; employment environment indicator; inventory levels indicator; manufacturing sector; new orders indicator; prediction accuracy; predictive error; predictive value; production indicator; purchase management index; supplier deliveries indicator; Autoregressive processes; Computational modeling; Educational institutions; Predictive models; Radial basis function networks; Time series analysis; PMI; RBF network; neural network ensemble;
Conference_Titel :
Computer Science & Service System (CSSS), 2012 International Conference on
Conference_Location :
Nanjing
Print_ISBN :
978-1-4673-0721-5
DOI :
10.1109/CSSS.2012.545
