arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2005.10111cs.LGstat.ML
收藏

离散化在预测中的有效性:神经时间序列模型的实证研究

The Effectiveness of Discretization in Forecasting: An Empirical Study on Neural Time Series Models

AWS AI Labs(AWS人工智能实验室);NAVER LABS Europe(NAVER欧洲实验室)

Stephan Rabanser, Tim Januschowski, Valentin Flunkert, David Salinas, Jan Gasthaus

摘要:

近年来,基于深度学习的时间序列建模技术取得了许多进展,特别是在数据丰富的环境中,其中心目标是学习可以跨多个时间序列提取模式的全局模型。虽然在以前的工作中经常注意到适当的数据预处理和缩放的至关重要性,但大多数研究都集中在改进模型架构上。在本文中,我们实证研究了数据输入和输出转换对几种神经预测架构的预测性能的影响。特别是,我们研究了几种形式的数据分箱的有效性,即将实值时间序列转换为分类序列,与前馈,递归神经网络和基于卷积的序列模型相结合。在这些模型非常成功的许多非预测应用中,模型输入和输出是分类的(例如,来自自然语言处理应用中的固定词汇表的单词或计算机视觉中的量化像素颜色强度)。对于预测应用程序,时间序列通常是实值的,已经提出了各种ad-hoc数据转换,但尚未进行系统的比较。为了解决这个问题,我们评估了上述模型类的实例在与不同类型的数据缩放和分箱相结合时的预测准确性。我们发现,装箱几乎总是提高性能(相比使用归一化的实值输入),但所选择的特定类型的装箱是不太重要的。

英文摘要:

Time series modeling techniques based on deep learning have seen many advancements in recent years, especially in data-abundant settings and with the central aim of learning global models that can extract patterns across multiple time series. While the crucial importance of appropriate data pre-processing and scaling has often been noted in prior work, most studies focus on improving model architectures. In this paper we empirically investigate the effect of data input and output transformations on the predictive performance of several neural forecasting architectures. In particular, we investigate the effectiveness of several forms of data binning, i.e. converting real-valued time series into categorical ones, when combined with feed-forward, recurrent neural networks, and convolution-based sequence models. In many non-forecasting applications where these models have been very successful, the model inputs and outputs are categorical (e.g. words from a fixed vocabulary in natural language processing applications or quantized pixel color intensities in computer vision). For forecasting applications, where the time series are typically real-valued, various ad-hoc data transformations have been proposed, but have not been systematically compared. To remedy this, we evaluate the forecasting accuracy of instances of the aforementioned model classes when combined with different types of data scaling and binning. We find that binning almost always improves performance (compared to using normalized real-valued inputs), but that the particular type of binning chosen is of lesser importance.

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。

↑