不依赖时间顺序，直接预测行为分布更准
How to model Human Actions distribution with Event Sequence Data
- 用显式分布预测替代传统顺序建模
- 简单方法比复杂模型更优，误差更低
- 适合零售、金融等关注结果而非时序的场景
本文研究人类行为序列中未来事件分布的预测问题，该任务在零售、金融、医疗和推荐系统等领域至关重要，其中精确的时间顺序往往不如结果集合重要。我们挑战主流的自回归范式，探究显式建模未来分布或无序多标记方法是否优于保留顺序的方法。通过分析局部顺序不变性，并引入基于KL散度的指标量化时间漂移，发现简单的显式分布预测目标始终优于复杂的隐式基线。进一步表明，预测类别模式崩溃主要由分布不平衡引起。本工作为模型策略选择提供了理论框架，并为构建更准确、鲁棒的预测系统提供实用指导。
原文摘要 · Abstract (English)
This paper studies forecasting of the future distribution of events in human action sequences, a task essential in domains like retail, finance, healthcare, and recommendation systems where the precise temporal order is often less critical than the set of outcomes. We challenge the dominant autoregressive paradigm and investigate whether explicitly modeling the future distribution or order-invariant multi-token approaches outperform order-preserving methods. We analyze local order invariance and introduce a KL-based metric to quantify temporal drift. We find that a simple explicit distribution forecasting objective consistently surpasses complex implicit baselines. We further demonstrate that mode collapse of predicted categories is primarily driven by distributional imbalance. This work provides a principled framework for selecting modeling strategies and offers practical guidance for building more accurate and robust forecasting systems.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。