可解释的多元时间序列预测：神经傅里叶变换
Interpretable Multivariate Time Series Forecasting Using Neural Fourier Transform
AI总结：
本文提出神经傅里叶变换（NFT）算法，结合多维傅里叶变换与时间卷积网络，在十四个数据集上验证了其高准确性和可解释性，为多元时间序列预测树立了新基准。
摘要：
多元时间序列预测在金融规划、医学诊断和气候科学等多个领域是一项关键任务。本文提出了神经傅里叶变换（Neural Fourier Transform, NFT）算法，该算法将多维傅里叶变换与时间卷积网络层相结合，以提高预测的准确性和可解释性。神经傅里叶变换在十四个不同数据集上进行了实证验证，在多个预测视界和回溯窗口上表现出优越性能，为该领域树立了新的基准。这项工作通过提供一种既具有可解释性又具有高预测能力的模型，推进了多元时间序列预测的发展，使其成为从业者和研究人员的有价值工具。本研究的代码已公开提供。
英文摘要：
Multivariate time series forecasting is a pivotal task in several domains, including financial planning, medical diagnostics, and climate science. This paper presents the Neural Fourier Transform (NFT) algorithm, which combines multi-dimensional Fourier transforms with Temporal Convolutional Network layers to improve both the accuracy and interpretability of forecasts. The Neural Fourier Transform is empirically validated on fourteen diverse datasets, showing superior performance across multiple forecasting horizons and lookbacks, setting new benchmarks in the field. This work advances multivariate time series forecasting by providing a model that is both interpretable and highly predictive, making it a valuable tool for both practitioners and researchers. The code for this study is publicly available.
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。
