About this document

1 s2.0 009813549280049F Main by phungtrieutan is a document available to read on EtoBox.

This study investigates the effectiveness of neural networks in forecasting short, noisy time series by comparing them to traditional methods like linear regression and exponential smoothing. Results indicate that while neural networks as function approximators generally performed worse than linear regression, they showed promise when used to combine traditional forecasts, yielding small but significant improvements. The findings suggest that neural networks can effectively learn to optimize forecasting met

Author

phungtrieutan

Language

EN