arXiv 2508.070162025-08-09cs.LGcs.IR

TLCCSP：一种利用时滞互相关增强时间序列预测的可扩展框架

TLCCSP: A Scalable Framework for Enhancing Time Series Forecasting with Time-Lagged Cross-Correlations

School of Artificial Intelligence（人工智能学院）；Institute of Artificial Intelligence and Future Networks（人工智能与未来网络研究所）；Department of Systems Science, Faculty of Arts and Sciences（艺术与科学学院系统科学系）；Guangdong Key Lab of AI and Multi-Modal Data Processing（广东人工智能与多模态数据处理重点实验室）；BNU-HKBU United International College（北师大-香港大学联合国际学院）

Jianfei Wu, Wenmian Yang, Bingning Liu, Weijia Jia

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

提出TLCCSP框架，通过SSDTW算法和对比学习编码器有效整合时滞互相关序列，在多领域数据集上显著降低预测均方误差并大幅缩减计算时间，实现了高可扩展性与实时性。

摘要：

时间序列预测在天气、金融和房地产预测等多个领域至关重要，因为准确的预测能支持明智的决策制定和风险缓解。尽管近期的深度学习模型提升了预测能力，但它们常忽略相关序列间的时滞互相关，而这对于捕捉复杂的时序关系至关重要。为此，我们提出了基于时滞互相关的序列预测框架（TLCCSP），通过有效整合时滞互相关序列来提升预测准确率。TLCCSP采用序列偏移动态时间规整（SSDTW）算法捕捉滞后相关性，并利用基于对比学习的编码器高效近似SSDTW距离。在天气、金融和房地产时间序列数据集上的实验结果证明了该框架的有效性。在天气数据集上，与单序列方法相比，SSDTW将均方误差（MSE）降低了16.01%，而对比学习编码器（CLE）进一步使MSE降低了17.88%。在股票数据集上，SSDTW实现了9.95%的MSE降幅，CLE则降低了6.13%。对于房地产数据集，SSDTW和CLE分别使MSE降低了21.29%和8.62%。此外，对比学习方法将SSDTW的计算时间减少了约99%，确保了在多时间序列预测任务中的可扩展性和实时适用性。

英文摘要：

Time series forecasting is critical across various domains, such as weather, finance and real estate forecasting, as accurate forecasts support informed decision-making and risk mitigation. While recent deep learning models have improved predictive capabilities, they often overlook time-lagged cross-correlations between related sequences, which are crucial for capturing complex temporal relationships. To address this, we propose the Time-Lagged Cross-Correlations-based Sequence Prediction framework (TLCCSP), which enhances forecasting accuracy by effectively integrating time-lagged cross-correlated sequences. TLCCSP employs the Sequence Shifted Dynamic Time Warping (SSDTW) algorithm to capture lagged correlations and a contrastive learning-based encoder to efficiently approximate SSDTW distances. Experimental results on weather, finance and real estate time series datasets demonstrate the effectiveness of our framework. On the weather dataset, SSDTW reduces mean squared error (MSE) by 16.01% compared with single-sequence methods, while the contrastive learning encoder (CLE) further decreases MSE by 17.88%. On the stock dataset, SSDTW achieves a 9.95% MSE reduction, and CLE reduces it by 6.13%. For the real estate dataset, SSDTW and CLE reduce MSE by 21.29% and 8.62%, respectively. Additionally, the contrastive learning approach decreases SSDTW computational time by approximately 99%, ensuring scalability and real-time applicability across multiple time series forecasting tasks.

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。