Metraipolis › archive › dc_99aa5c38726b

TempShap: When and How Much a Feature Matters in Time-Series Forecasting — arXiv:2610.33330

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.33330
License (as archived)
CC0-1.0
Archived
2026-10-27T07:56:32.729Z
SHA-256 of the archived text
60b51a0c754d2ddbb9d72192d17d72f8e63bca6c582d9b01558f67a8476dfe7a
Stable URL of this page
https://metraipolis.com/documento/dc_99aa5c38726b

How to cite

TempShap: When and How Much a Feature Matters in Time-Series Forecasting — arXiv:2610.33330 — arXiv (en), https://arxiv.org/abs/2610.33330 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_99aa5c38726b (Metraipolis archive dc_99aa5c38726b, sha256 60b51a0c754d2ddbb9d72192d17d72f8e63bca6c582d9b01558f67a8476dfe7a)
BibTeX
@misc{dc99aa5c38726b,
  title = {TempShap: When and How Much a Feature Matters in Time-Series Forecasting — arXiv:2610.33330},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.33330},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_99aa5c38726b; sha256 60b51a0c754d2ddbb9d72192d17d72f8e63bca6c582d9b01558f67a8476dfe7a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.33330. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Attribution for a time-series forecaster should answer two questions that a feature-level scalar cannot: when in the input window a feature acts, and how much its influence changes across the forecast horizon. Most existing Shapley explainers treat each feature as one player and therefore collapse both axes. We propose TempShap, a retrospective, loss-based Shapley framework whose players are the individual input cells $(t,i)$. Its attribution tensor yields temporal-localization and horizon-impact profiles. We validate these against planted temporal structures, a tractable exact cell game, and a closed-form attribution oracle for a real linear forecaster. Permutation sharing estimates the cell-level game at localized perturbation cost. Under redundant inputs, one-at-a-time scores under-credit substitutable information, whereas the signed Shapley decomposition preserves total value and yields more reliable held-out deletion rankings under mean masking. A planted counterexample isolates the redundancy mechanism. Experiments show a deletion-ranking advantage across Shapley estimators, forecasting benchmarks, and model families. TempShap therefore makes fine-grained Shapley attribution both practical and operationally useful.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computer Science and Game Theory (cs.GT); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.33330 — 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 2026-10-27T07:55:30.630Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).