用2D掩码预训练模型预测旅游行程时间序列，效果优于现有方法。
TripCast: Pre-training of Masked 2D Transformers for Trip Time Series Forecasting
- 将行程时间序列视为2D数据，通过掩码重建方式预训练
- 在真实数据上预训练，域内预测性能领先，域外迁移能力强
- 适合需要高精度旅游流量预测的场景，如景区调度
深度学习与预训练模型在时间序列预测中表现卓越。然而，在旅游业中，时间序列常具有前瞻性特征，呈现二维结构，带来独特挑战。本文提出一种新范式TripCast，将行程时间序列视为二维数据，通过掩码与重构过程学习表征。在大规模真实数据上预训练后，TripCast在域内预测任务中显著优于其他先进基线，并在域外预测中展现出强大的可扩展性与迁移能力。
原文摘要 · Abstract (English)
Deep learning and pre-trained models have shown great success in time series forecasting. However, in the tourism industry, time series data often exhibit a leading time property, presenting a 2D structure. This introduces unique challenges for forecasting in this sector. In this study, we propose a novel modelling paradigm, TripCast, which treats trip time series as 2D data and learns representations through masking and reconstruction processes. Pre-trained on large-scale real-world data, TripCast notably outperforms other state-of-the-art baselines in in-domain forecasting scenarios and demonstrates strong scalability and transferability in out-domain forecasting scenarios.
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。