Time series refer to a series of data points indexed in time order, which can be found in various fields, e.g., transportation, healthcare, and finance. Accurate time series forecasting can enhance optimization planning and decision-making support. Time series have multi-scale characteristics, i.e., different temporal patterns at different scales, which presents a challenge for time series forecasting. In this paper, we propose TPRNN, a Top-down Pyramidal Recurrent Neural Network for time series forecasting. We first construct subsequences of different scales from the input, forming a pyramid structure. Then by executing a multi-scale information interaction module from top to bottom, we model both the temporal dependencies of each scale and the influences of subsequences of different scales, resulting in a complete modeling of multi-scale temporal patterns in time series. Experiments on seven real-world datasets demonstrate that TPRNN has achieved the state-of-the-art performance with an average improvement of 8.13% in MSE compared to the best baseline.

翻译：时间序列是指按时间顺序索引的一系列数据点，广泛存在于交通、医疗和金融等领域。准确的时间序列预测能够优化规划决策并提升决策支持能力。时间序列具有多尺度特性，即不同尺度下呈现不同的时间模式，这给时间序列预测带来了挑战。本文提出TPRNN，一种用于时间序列预测的自顶向下金字塔循环神经网络。我们首先从输入中构建不同尺度的子序列，形成金字塔结构；随后通过自顶向下执行多尺度信息交互模块，建模各尺度的时间依赖关系以及不同尺度子序列之间的相互影响，从而实现对时间序列中多尺度时间模式的完整建模。在七个真实数据集上的实验表明，与最优基线相比，TPRNN实现了最先进的性能，MSE平均提升8.13%。