What question did this study set out to answer?

This study aims to evaluate the performance of series and parallel strategies for financial time series forecasting.

November 6, 2017Financial InnovationOpen Access

Performance evaluation of series and parallel strategies for financial time series forecasting

View Full Paper

Ask AI

Bookmark

Authors

Randomized trial evaluating forecasting accuracy of series and parallel strategies in finance, indicating one may be more effective.

This study aims to evaluate the performance of series and parallel strategies for financial time series forecasting.
Constructed five hybrid models using series and parallel strategies based on ARIMA and MLPs.
Compared models with each other and with their base models for forecasting stock prices.
Utilized two benchmark datasets: Shenzhen Integrated Index (SZII) and Standard and Poor’s 500 (S&P 500).
All hybrid models outperformed at least one individual component.
The series combination strategy produced more accurate forecasting results.
Performance was evaluated on the SZII and S&P 500 datasets.

Khashei et al. (2017) studied this question.

View Full Paper

Ask AI

Bookmark