EUVIMEDEUVIMED entdecken
Crossref

Towards Transparent Time Series Analysis: Exploring Methods and Enhancing Interpretability

Youngjin Park, Anh Tong, Sehyun Lee, Jihyeon Seong, Qin Xie, Jaesik Choi

ACM Computing Surveys · 31.07.2026 · 58 (9) · 1-36

DOI: 10.1145/3794839 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Computing Surveys, online erschienen am 10.03.2026. Verfasst von Youngjin Park und 5 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 214 Literaturangaben. Gefördert von: Institute for Information & communications Technology Planning & Evaluation, Korea Planning & Evaluation Institute of Industrial Technology.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This article presents a comprehensive cross-task analysis of time series methodologies, revealing fundamental connections that are often obscured by task-specific perspectives. Our contributions are fivefold. First, we introduce seven priority properties, along with exogenous integration, that characterize methodologies independent of application domain, enabling systematic comparison across traditional and modern approaches. Second, we classify neural architectures by transparency levels determined by two characteristics: parameter time-invariance and the explicitness of mathematical formulations. Locally time-invariant operations enable mechanistic understanding, but globally time-varying operations pose fundamental challenges to achieving it. Third, our hierarchical taxonomy guides the selection of methodologies. Fourth, we comparatively evaluate explanation methods by quantifying how closely they recover transparency, measuring explanation richness via breadth (granularity) and depth (mechanistic understanding): pointwise methods offer lower richness, component-level methods achieve medium richness, and concept-based methods achieve higher richness, sometimes at the cost of generalization. Finally, we identify an ongoing challenge from the absence of ground truth for temporal components and outline future research directions for time-varying modeling explanations. This survey provides methodological insights and practical frameworks in time series analysis.

Förderung

  • Institute for Information & communications Technology Planning & Evaluation
  • Korea Planning & Evaluation Institute of Industrial Technology

Zitieren

APA

Park, Y., Tong, A., Lee, S., Seong, J., Xie, Q., & Choi, J. (2026). Towards Transparent Time Series Analysis: Exploring Methods and Enhancing Interpretability. ACM Computing Surveys, 58(9), 1-36. https://doi.org/10.1145/3794839

Vancouver

Park Y, Tong A, Lee S, Seong J, Xie Q, Choi J. Towards Transparent Time Series Analysis: Exploring Methods and Enhancing Interpretability. ACM Computing Surveys. 2026;58(9):1-36. doi:10.1145/3794839

BibTeX
@article{Park2026,
  author = {Park, Youngjin and Tong, Anh and Lee, Sehyun and Seong, Jihyeon and Xie, Qin and Choi, Jaesik},
  title = {Towards Transparent Time Series Analysis: Exploring Methods and Enhancing Interpretability},
  journal = {ACM Computing Surveys},
  year = {2026},
  volume = {58},
  number = {9},
  pages = {1--36},
  doi = {10.1145/3794839}
}
Kostenlos starten →