发表机构
Beijing Jiaotong University; Didichuxing Co. Ltd; Lancaster University（北京交通大学; 滴滴出行有限公司; 兰卡斯特大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对动态交通环境下行程时间预测精度不足问题，提出双阶段持续学习框架DSETA，结合日内与日间间学习及知识整合模块，在滴滴真实数据集上实现MAE下降并成功落地应用。
AI 中文摘要
预计到达时间（ETA）预测是智能交通系统的核心组成部分。随着大城市交通拥堵模式日益动态，保持高预测精度成为网约车平台面临的重大挑战。现有方法要么无法适应不规则交通模式和突发拥堵，要么在未解耦长期趋势与短期波动的情况下处理新分布，导致模型在实际场景中性能下降。为应对该挑战，我们提出DSETA，一种增量更新的双阶段ETA预测框架。具体而言，持续学习过程分为日间间（inter-day）和日内（intra-day）两个阶段。我们首先设计日内学习阶段，该阶段完全依赖实时数据，以动态适应节假日或事故等事件引发的短期交通模式。接着，我们开发日间间学习阶段，该阶段利用短时间窗口内的聚合历史数据，捕捉长期分布偏移的知识，如季节性趋势和交通网络演变。随后，为防止灾难性遗忘并保留常规模式知识，我们探索了历史交通知识整合（Historical Traffic Knowledge Consolidation）模块。最后，我们通过在滴滴平台真实数据集上开展的大量离线和在线实验，验证DSETA的有效性与鲁棒性。在北京、武汉、西安三个主要城市开展的在线A/B测试均显示性能提升，分别实现平均绝对误差（MAE）降低6.62%、0.73%和2.40%。该框架已成功部署于滴滴生产环境，每日处理数亿次请求，在工业应用中验证了其强劲性能。
英文摘要
Estimated Time of Arrival (ETA) prediction is a core component of intelligent transportation systems. As traffic congestion patterns become increasingly dynamic in large cities, maintaining high prediction accuracy poses a major challenge for ride-hailing platforms. Existing methods either fail to adapt to irregular traffic patterns and sudden congestion, or suffer from new distributions without disentangling long-term trends from short-term fluctuations, thereby degrading model performance in real-world scenarios. To address this challenge, we propose DSETA, an incrementally updated Dual-Stage ETA prediction framework. Specifically, the continual learning process is divided into \textit{inter-day} and \textit{intra-day} stages. We first design the \textit{intra-day} learning stage, which relies entirely on real-time data to enable dynamic adaptation to short-term traffic patterns caused by events like holidays or accidents. Next, we develop the \textit{inter-day} learning stage, which leverages aggregated historical data from a short time window to capture knowledge of long-term distribution shifts, such as seasonal trends and traffic network evolution. Subsequently, to prevent catastrophic forgetting and preserve knowledge of regular patterns, we explore a \textit{Historical Traffic Knowledge Consolidation} module. Finally, we validate DSETA's effectiveness and robustness through extensive offline and online experiments conducted on real-world datasets from DiDi's platform. Online A/B tests across three major cities including Beijing, Wuhan, and Xi'an consistently demonstrated performance gains, achieving MAE reductions of 6.62\%, 0.73\%, and 2.40\% respectively. This framework has been successfully deployed in DiDi's production environment, processing hundreds of millions of daily requests and validating its strong performance in industrial applications.
