A Hybrid Model Using PCA and BP Neural Network for Time Series Prediction in Chinese Stock Market with TOPSIS Analysis

Table 8

Summary of PCA-BP neural network with different training algorithms.

Performance index	PCA-BP_LM	PCA-BP_BR	PCA-BP_SCG
MSE	1.8505	0.6835	465.9897
RMSE	1.3603	0.8267	21.5868
MAPE	0.0204	0.0130	0.4137
Accuracy5	0.9433	0.9967	0.0000
Accuracy	0.9506	0.9947	0.1173

RMSE, root mean square error. Bold values signify the best results.