Paper Detail

Realism VS Accuracy: Event Sequence Forecasting from a Generative Modeling Perspective

Dmitry Osin, Egor Surkov, Petr Mokrov, Igor Udovichenko, Ivan Karpukhin, Evgeny Burnaev, Egor Shvetsov, Alexander Korotin

huggingface Score 9.5

Published 2026-10-08 · First seen 2026-10-24

General AI

Abstract

Event sequences are chains of random events, each described by heterogeneous (numerical and categorical) features. The problem of event sequence forecasting occurs in finance, healthcare, business process intelligence, and other fields. In this work, we study multi-horizon forecasting of event sequences as a conditional generative modeling problem. We evaluate forecasts not only for prediction accuracy, but also for distributional realism. To this end, we present a benchmark comprising metrics for both quality aspects, strong statistical baselines, recent models adapted from adjacent fields, and curated real-world datasets. Careful evaluation reveals that no method excels at both accuracy and realism, highlighting a fundamental trade-off between the two. Finally, we introduce Wasserstein BaryBooster, an algorithm that aggregates samples from a realism-strong diffusion model into a state-of-the-art predictor, demonstrating that distributional realism can be converted into prediction accuracy. Code is available at https://github.com/xaosina/event-sequence-forecasting.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
soon
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@misc{osin2026realism,
  title = {Realism VS Accuracy: Event Sequence Forecasting from a Generative Modeling Perspective},
  author = {Dmitry Osin and Egor Surkov and Petr Mokrov and Igor Udovichenko and Ivan Karpukhin and Evgeny Burnaev and Egor Shvetsov and Alexander Korotin},
  year = {2026},
  abstract = {Event sequences are chains of random events, each described by heterogeneous (numerical and categorical) features. The problem of event sequence forecasting occurs in finance, healthcare, business process intelligence, and other fields. In this work, we study multi-horizon forecasting of event sequences as a conditional generative modeling problem. We evaluate forecasts not only for prediction accuracy, but also for distributional realism. To this end, we present a benchmark comprising metrics f},
  url = {https://huggingface.co/papers/2610.12586},
  keywords = {multi-horizon forecasting, conditional generative modeling, diffusion model, Wasserstein BaryBooster, code available, huggingface daily},
  eprint = {2610.12586},
  archiveprefix = {arXiv},
}

Metadata

{}