Metraipolis › archive › dc_565dcc71c428

EventGPT: Next-Event Pretraining on Banking Customer Histories — arXiv:2611.03302

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.03302
License (as archived)
CC0-1.0
Archived
2026-11-03T11:26:47.342Z
SHA-256 of the archived text
f5c7fad066d613571c4bb5379e57e5d348db546db6f34e638799d4388ebe5c13
Stable URL of this page
https://metraipolis.com/documento/dc_565dcc71c428

How to cite

EventGPT: Next-Event Pretraining on Banking Customer Histories — arXiv:2611.03302 — arXiv (en), https://arxiv.org/abs/2611.03302 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_565dcc71c428 (Metraipolis archive dc_565dcc71c428, sha256 f5c7fad066d613571c4bb5379e57e5d348db546db6f34e638799d4388ebe5c13)
BibTeX
@misc{dc565dcc71c428,
  title = {EventGPT: Next-Event Pretraining on Banking Customer Histories — arXiv:2611.03302},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.03302},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_565dcc71c428; sha256 f5c7fad066d613571c4bb5379e57e5d348db546db6f34e638799d4388ebe5c13},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.03302. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

A model pretrained to predict a customer's next event can estimate the probability of future events without training on their labels and provide a reusable representation for supervised downstream banking tasks. We pretrain EventGPT, a hierarchical causal transformer, by next-token maximum likelihood estimation on the public Multimodal Banking Dataset (MBD-mini: 100,224 clients, 38.8 million transactions and 66.3 million geolocation pings). Keeping one state per event, EventGPT trains in about two hours on one L4 GPU at windows up to 8,192 tokens. From its next-event distribution, with no labels, EventGPT scores five targets of the form "the client makes a transaction of a given kind for the first time next month" at ROC-AUC 0.79 to 0.92. Gradient boosting on 114 engineered features needs 10,000 to 300,000 labeled client-months to match it on four targets and stays below it on the fifth. For product prediction, frozen EventGPT embeddings score below the engineered features (mean ROC-AUC 0.787 against 0.808 over five test folds), and a rank-averaged ensemble of EventGPT, profile fields and token counts with the engineered features adds 0.014 to 0.017, of which 0.007 to 0.016 is EventGPT's own. The code and pretrained weights are released.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (stat.ML) ; Machine Learning (cs.LG); Statistical Finance (q-fin.ST).
Pagina del lavoro: https://arxiv.org/abs/2611.03302 — 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 2026-11-03T11:02:37.907Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).