Metraipolis › archive › dc_057b08df1d8a

Probabilistic Forecasting of Business Process Executions with Neural Temporal Point Processes — arXiv:2609.21382

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.21382
License (as archived)
CC0-1.0
Archived
2026-10-10T01:45:03.312Z
SHA-256 of the archived text
0c342eb8217f942cc50cd279149721d5feacbcf342fc85f2968c3da5f649bff4
Stable URL of this page
https://metraipolis.com/documento/dc_057b08df1d8a

How to cite

Probabilistic Forecasting of Business Process Executions with Neural Temporal Point Processes — arXiv:2609.21382 — arXiv (en), https://arxiv.org/abs/2609.21382 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_057b08df1d8a (Metraipolis archive dc_057b08df1d8a, sha256 0c342eb8217f942cc50cd279149721d5feacbcf342fc85f2968c3da5f649bff4)
BibTeX
@misc{dc057b08df1d8a,
  title = {Probabilistic Forecasting of Business Process Executions with Neural Temporal Point Processes — arXiv:2609.21382},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.21382},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_057b08df1d8a; sha256 0c342eb8217f942cc50cd279149721d5feacbcf342fc85f2968c3da5f649bff4},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.21382. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Operators of service-based systems act on forecasts of how a running execution will continue, and such a forecast is actionable only if its reliability is known. Mainstream deep-learning models for this task are discriminative and deterministic: they emit a single next activity and a single remaining-time estimate, without a distribution to reason over. We instead cast the problem as generative sequence modelling with marked temporal point processes, which define a joint density over the next mark and its inter-event time and therefore deliver predictive distributions by construction. Real event logs violate the simple-point-process assumption these models rest on, since consecutive events frequently carry identical timestamps; we handle such ties explicitly and combine a transformer encoder with a mixture decoder over inter-event times, trained by exact log-likelihood. On ten public logs, the resulting model matches discriminative baselines on point accuracy, dominates them on the calibration and sharpness of remaining-time distributions, and is the cheapest at inference, since a full predictive distribution is obtained in a single forward pass without sampling.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-21 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.21382 — 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 2026-10-10T01:14:16.627Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-21?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).