Metraipolis › archive › dc_830e72d0f9ba

TAPES: Task-Aligned Joint Predictive Pretraining for Transaction Event Sequences — arXiv:2611.04747

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.04747
License (as archived)
CC0-1.0
Archived
2026-11-04T18:37:19.019Z
SHA-256 of the archived text
cb7a872a6d9c9648201f086b2eb410a7e30b6a937cde5e8669d861ca95c2d65e
Stable URL of this page
https://metraipolis.com/documento/dc_830e72d0f9ba

How to cite

TAPES: Task-Aligned Joint Predictive Pretraining for Transaction Event Sequences — arXiv:2611.04747 — arXiv (en), https://arxiv.org/abs/2611.04747 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_830e72d0f9ba (Metraipolis archive dc_830e72d0f9ba, sha256 cb7a872a6d9c9648201f086b2eb410a7e30b6a937cde5e8669d861ca95c2d65e)
BibTeX
@misc{dc830e72d0f9ba,
  title = {TAPES: Task-Aligned Joint Predictive Pretraining for Transaction Event Sequences — arXiv:2611.04747},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.04747},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_830e72d0f9ba; sha256 cb7a872a6d9c9648201f086b2eb410a7e30b6a937cde5e8669d861ca95c2d65e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.04747. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Transaction event sequences support diverse prediction tasks in online commerce and digital financial services. The same transaction records can yield prediction targets with different semantics, including values, changes, and relations to past events. These targets impose different constraints on history representations, but their predictability alone does not establish the downstream utility of a target set. Moreover, target-wise prediction losses do not explicitly model conditional co-occurrence among targets. To address these challenges, we propose TAPES, a task-aligned joint predictive pretraining framework for transaction sequences. TAPES constructs a finite collection of candidate target sets from admissible field-operator combinations. It selects a target set according to the downstream utility of representations learned through short joint pretraining trials under matched budgets. It then reinitializes the encoder and pretrains it on the selected targets through a joint likelihood parameterized by a shared discrete latent variable, before downstream supervised adaptation. Experiments in a real-world transaction-risk setting and on multiple public financial benchmarks spanning diverse downstream tasks demonstrate that TAPES outperforms representative baselines. Ablation studies further validate the contributions of predictive target selection and joint modeling.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.04747 — 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 2026-11-04T18:32:37.462Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).