Multichannel SSA decomposition in a hybrid SSA–N-BEATS framework for complex time series forecasting
Alfian Adi Pratama, Putriaji Hendikawati · 2026
Read Multichannel SSA decomposition in a hybrid SSA–N-BEATS framework for complex time series forecasting by Alfian Adi Pratama, Putriaji Hendikawati (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13632226.txt.
Description
Alfian Adi Pratama and Putriaji Hendikawati benchmark a hybrid forecasting framework for complex time series. Their 2026 paper joins singular spectrum analysis with the N-BEATS network. Raw series mix trends, seasons, and high-frequency noise. Neural forecasters can stumble when fed such tangled signals. Decomposition before training offers a practical fix.
Two hybrid designs were tested against plain N-BEATS. One used decomposition only to denoise the input. The other split the series into trend and seasonal channels. Each channel then ran through its own network path. Evaluation covered calm periods and stretches with structural breaks. The protocol checks how hybrids behave when data turn unstable. Results guide hybrid design for hard forecasting tasks.
Catalog record
| CREATOR | Alfian Adi Pratama, Putriaji Hendikawati |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 115 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |