TripCast：面向出行时间序列预测的掩码 2D Transformer 预训练
TripCast: Pre-training of Masked 2D Transformers for Trip Time Series Forecasting
AI总结：
针对旅游业具有前置时间特性的二维出行时间序列，提出 TripCast 建模范式，通过掩码与重建进行二维 Transformer 预训练，在域内和域外预测中取得优异性能。
摘要：
深度学习与预训练模型已在时间序列预测中取得巨大成功。然而，在旅游业中，时间序列数据通常表现出前置时间特性，并呈现二维结构。这给该领域的预测带来了独特挑战。在本研究中，我们提出一种新颖建模范式 TripCast，它将出行时间序列视为二维数据，并通过掩码与重建过程学习表示。TripCast 在大规模真实世界数据上进行预训练，在域内预测场景中显著优于其他最先进基线，并在域外预测场景中展现出强大的可扩展性与可迁移性。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
