Detecting the Future: All-at-Once Event Sequence Forecasting with Horizon Matching

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Karpukhin, Ivan, Savchenko, Andrey
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915654810992640
author Karpukhin, Ivan
Savchenko, Andrey
author_facet Karpukhin, Ivan
Savchenko, Andrey
contents Long-horizon events forecasting is a crucial task across various domains, including retail, finance, healthcare, and social networks. Traditional models for event sequences often extend to forecasting on a horizon using an autoregressive (recursive) multi-step strategy, which has limited effectiveness due to typical convergence to constant or repetitive outputs. To address this limitation, we introduce DEF, a novel approach for simultaneous forecasting of multiple future events on a horizon with high accuracy and diversity. Our method optimally aligns predictions with ground truth events during training by using a novel matching-based loss function. We establish a new state-of-the-art in long-horizon event prediction, achieving up to a 50% relative improvement over existing temporal point processes and event prediction models. Furthermore, we achieve state-of-the-art performance in next-event prediction tasks while demonstrating high computational efficiency during inference.
format Preprint
id arxiv_https___arxiv_org_abs_2408_13131
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Detecting the Future: All-at-Once Event Sequence Forecasting with Horizon Matching
Karpukhin, Ivan
Savchenko, Andrey
Machine Learning
Artificial Intelligence
Long-horizon events forecasting is a crucial task across various domains, including retail, finance, healthcare, and social networks. Traditional models for event sequences often extend to forecasting on a horizon using an autoregressive (recursive) multi-step strategy, which has limited effectiveness due to typical convergence to constant or repetitive outputs. To address this limitation, we introduce DEF, a novel approach for simultaneous forecasting of multiple future events on a horizon with high accuracy and diversity. Our method optimally aligns predictions with ground truth events during training by using a novel matching-based loss function. We establish a new state-of-the-art in long-horizon event prediction, achieving up to a 50% relative improvement over existing temporal point processes and event prediction models. Furthermore, we achieve state-of-the-art performance in next-event prediction tasks while demonstrating high computational efficiency during inference.
title Detecting the Future: All-at-Once Event Sequence Forecasting with Horizon Matching
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2408.13131