arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1902.07892q-fin.CPcs.LG
收藏

用于时间序列预测的深度自适应输入归一化

Deep Adaptive Input Normalization for Time Series Forecasting

Tampere University(坦佩雷大学);Aristotle University of Thessaloniki(塞萨洛尼基亚里士多德大学);Aarhus University(奥胡斯大学)

Nikolaos Passalis, Anastasios Tefas, Juho Kanniainen, Moncef Gabbouj, Alexandros Iosifidis

摘要:

深度学习(DL)模型可以用来处理时间序列分析任务,并取得巨大成功。然而,如果数据没有被适当地归一化,DL模型的性能会迅速退化。当DL用于金融时间序列预测任务时,这个问题更加明显,其中数据的非平稳和多模态性质构成了重大挑战,并严重影响了DL模型的性能。在这项工作中,一个简单的,但有效的,神经层,这是能够自适应规范化的输入时间序列,同时考虑到数据的分布,提出。所提出的层使用反向传播以端到端的方式进行训练,与其他评估的归一化方案相比,性能得到了显着提高。所提出的方法不同于传统的归一化方法,因为它学习如何为给定的任务执行归一化,而不是使用固定的归一化方案。同时,它可以直接应用于任何新的时间序列,而不需要重新训练。使用一个大规模的限价订单簿数据集,以及负荷预测数据集证明了所提出的方法的有效性。

英文摘要:

Deep Learning (DL) models can be used to tackle time series analysis tasks with great success. However, the performance of DL models can degenerate rapidly if the data are not appropriately normalized. This issue is even more apparent when DL is used for financial time series forecasting tasks, where the non-stationary and multimodal nature of the data pose significant challenges and severely affect the performance of DL models. In this work, a simple, yet effective, neural layer, that is capable of adaptively normalizing the input time series, while taking into account the distribution of the data, is proposed. The proposed layer is trained in an end-to-end fashion using back-propagation and leads to significant performance improvements compared to other evaluated normalization schemes. The proposed method differs from traditional normalization methods since it learns how to perform normalization for a given task instead of using a fixed normalization scheme. At the same time, it can be directly applied to any new time series without requiring re-training. The effectiveness of the proposed method is demonstrated using a large-scale limit order book dataset, as well as a load forecasting dataset.

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。

↑