Metraipolis › archive › dc_8c2d0d67dfaa
SynForecast: Controlled Synthetic Time Series for Forecasting Research — arXiv:2611.02802
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.02802
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T18:38:42.396Z
- SHA-256 of the archived text
26fc1bb6c3d30a8f1f76fb7114fd6f5838907d8cdc5a7dc844b924f0cdf26cb8- Stable URL of this page
https://metraipolis.com/documento/dc_8c2d0d67dfaa
How to cite
SynForecast: Controlled Synthetic Time Series for Forecasting Research — arXiv:2611.02802 — arXiv (en), https://arxiv.org/abs/2611.02802 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8c2d0d67dfaa (Metraipolis archive dc_8c2d0d67dfaa, sha256 26fc1bb6c3d30a8f1f76fb7114fd6f5838907d8cdc5a7dc844b924f0cdf26cb8)
BibTeX
@misc{dc8c2d0d67dfaa,
title = {SynForecast: Controlled Synthetic Time Series for Forecasting Research — arXiv:2611.02802},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.02802},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8c2d0d67dfaa; sha256 26fc1bb6c3d30a8f1f76fb7114fd6f5838907d8cdc5a7dc844b924f0cdf26cb8},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.02802. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Synthetic time series constitute a substantial share of the training corpora of several recent forecasting foundation models. Existing studies report benefits at small data budgets and modest synthetic proportions, but each evaluates individual combinations of model and generator. Studying these benefits systematically requires generators that support controlled configuration, perturbation, reproducibility and mechanism-level ablation, and the 11 existing generators we review show gaps in this combined support. We present SynForecast, an open-source Python library with 32 generators, 19 of which implement named mechanisms with a published source in econometrics, quantitative finance, statistical physics and point-process theory. Perturbations and mechanism families can be varied while everything else is held fixed, output comes in the long format that forecasting libraries accept, and output does not depend on the number of parallel workers. We evaluate SynForecast on M4 at five frequencies with a neural network and a gradient-boosted ensemble. A classical baseline attains the lowest error in nine of ten frequency-history combinations. A synthetic prior outperforms the same network trained from scratch at a fixed budget by up to 34% with a few dozen observations, but loses to it at full history at every frequency, and none of three pre-specified rescalings of history predicts where the sign changes. At the hourly frequency, where the prior fails at every history, the corpus lacks daily cycles; adding them reduces zero-shot error by 43 to 63% for both models. Fine-tuning outperforms training from scratch by up to about 15%, but at short histories a fixed 300-step fine-tune is worse than the pretrained model used as is. Removing the classical mechanism family costs about 2% for both models; every other family has a smaller effect outside the hourly frequency. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG) ; Computation (stat.CO). Pagina del lavoro: https://arxiv.org/abs/2611.02802 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-03T18:12:54.589Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).