Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2507.13556 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908455451754496 |
|---|---|
| author | Wang, Rui Klee, Steven Roos, Alexis |
| author_facet | Wang, Rui Klee, Steven Roos, Alexis |
| contents | This paper proposes using two metrics to quantify the forecastability of time series prior to model development: the spectral predictability score and the largest Lyapunov exponent. Unlike traditional model evaluation metrics, these measures assess the inherent forecastability characteristics of the data before any forecast attempts. The spectral predictability score evaluates the strength and regularity of frequency components in the time series, whereas the Lyapunov exponents quantify the chaos and stability of the system generating the data. We evaluated the effectiveness of these metrics on both synthetic and real-world time series from the M5 forecast competition dataset. Our results demonstrate that these two metrics can correctly reflect the inherent forecastability of a time series and have a strong correlation with the actual forecast performance of various models. By understanding the inherent forecastability of time series before model training, practitioners can focus their planning efforts on products and supply chain levels that are more forecastable, while setting appropriate expectations or seeking alternative strategies for products with limited forecastability. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_13556 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Time Series Forecastability Measures Wang, Rui Klee, Steven Roos, Alexis Machine Learning Artificial Intelligence This paper proposes using two metrics to quantify the forecastability of time series prior to model development: the spectral predictability score and the largest Lyapunov exponent. Unlike traditional model evaluation metrics, these measures assess the inherent forecastability characteristics of the data before any forecast attempts. The spectral predictability score evaluates the strength and regularity of frequency components in the time series, whereas the Lyapunov exponents quantify the chaos and stability of the system generating the data. We evaluated the effectiveness of these metrics on both synthetic and real-world time series from the M5 forecast competition dataset. Our results demonstrate that these two metrics can correctly reflect the inherent forecastability of a time series and have a strong correlation with the actual forecast performance of various models. By understanding the inherent forecastability of time series before model training, practitioners can focus their planning efforts on products and supply chain levels that are more forecastable, while setting appropriate expectations or seeking alternative strategies for products with limited forecastability. |
| title | Time Series Forecastability Measures |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2507.13556 |