Fig 1.
Feedforward Backpropagation Neural Network architecture.
Fig 2.
Continuously datasets arrangement for training and evaluation, 2005–2014.
Fig 3.
Architecture of the proposed models.
Table 1.
Wavelet families and subsets.
Fig 4.
Univariate (Wavelet) and Multivariate (Wavelet-PCA) Denoising of Hang Seng futures 2014.
Fig 5.
Univariate (Wavelet) and Multivariate (Wavelet-PCA) Denoising of KOSPI 200 futures 2014.
Fig 6.
Univariate (Wavelet) and Multivariate (Wavelet-PCA) Denoising of NIKKEI 225 futures 2014.
Fig 7.
Univariate (Wavelet) and Multivariate (Wavelet-PCA) Denoising of SiMSCI futures 2014.
Fig 8.
Univariate (Wavelet) and Multivariate (Wavelet-PCA) Denoising of TAIEX futures 2014.
Fig 9.
Research framework for models 1 and 2.
Table 2.
Settings of the best-performing networks.
Table 3.
Performance of the models, MAPE ratio of evaluation results for HANG SENG futures.
Table 4.
Return of the models, results for HANG SENG futures.
Table 5.
Performance of the models, MAPE ratio of evaluation results for KOSPI futures.
Table 6.
Return of the models, results for KOSPI futures.
Table 7.
Performance of the models, MAPE ratio of evaluation results for NIKKEI 225 futures.
Table 8.
Return of the models, results for NIKKEI 225 futures.
Table 9.
Performance of the models, MAPE ratio of evaluation results for SiMSCI futures.
Table 10.
Profit of the models, results for SiMSCI futures.
Table 11.
Performance of the models, MAPE ratio of evaluation results for TAIEX futures.
Table 12.
Profit of the models, results for TAIEX futures.
Fig 10.
Forecasting results of all models for Hang Seng futures in 2014.
Fig 11.
Forecasting results of all models for KOSPI 200 futures in 2014.
Fig 12.
Forecasting results of all models for NIKKEI 225 futures in 2014.
Fig 13.
Forecasting results of all models for SiMSCI futures in 2014.
Fig 14.
Forecasting results of all models for TAIEX futures in 2014.
Table 13.
Summary of forecasting performance, MAPE ratio, from 2005 to 2014.
Table 14.
Summary of Average Annual Returns from 2005 to 2014.