| Autor: |
Melih Barsbey, Ali Taylan Cemgil |
| Jazyk: |
angličtina |
| Rok vydání: |
2023 |
| Předmět: |
|
| Zdroj: |
IEEE Access, Vol 11, Pp 85770-85784 (2023) |
| Druh dokumentu: |
article |
| ISSN: |
2169-3536 |
| DOI: |
10.1109/ACCESS.2023.3298597 |
| Popis: |
Accurately representing periodic behavior is a frequently encountered challenge in modeling time series. This is especially true for observations where multiple, nested seasonalities are present, which is often encountered in data that pertain to collective human activity. In this work, we propose a new method that models seasonality through the multilinear representations that characterize low-rank tensor decompositions. We show that the tensor formalism accurately describes multiple nested periodic patterns, and well-known tensor decompositions can be used to parametrize cyclical patterns, leading to superior generalization and parameter efficiency. Furthermore, we develop a Bayesian variant of our approach which facilitates extraction of these seasonal patterns in an interpretable fashion from large-scale datasets, providing insight into the underlying dynamics that create such emergent behavior. We lastly test our method in missing data imputation, where the results show that our method couples interpretability with accuracy in time series analysis. |
| Databáze: |
Directory of Open Access Journals |
| Externí odkaz: |
|
