Interpretable Multivariate Time Series Forecasting Using Neural Fourier Transform
This provides an interpretable and predictive model for practitioners and researchers in fields like finance and medicine, though it appears incremental as it combines existing techniques.
The paper tackled multivariate time series forecasting by introducing the Neural Fourier Transform algorithm, which improved accuracy and interpretability, achieving superior performance on fourteen datasets and setting new benchmarks.
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.