Modular Neural Networks for Time Series Forecasting: Interpretability and Feature Selection using Attention

arXiv:2311.16834v3 Announce Type: replace
Abstract: Multivariate time series have many applications, from healthcare and meteorology to life science. Although deep learning models have shown excellent predictive performance for time series, they have been criticised for being "black-boxes" or non-interpretable. This paper proposes a novel modular neural network model for multivariate time series prediction that is interpretable by construction. A recurrent neural network learns the temporal dependencies in the data while an attention-based feature selection component selects the most relevant features …

abstract applications arxiv attention cs.ai cs.lg deep learning feature feature selection forecasting healthcare interpretability life meteorology modular multivariate network networks neural network neural networks novel paper performance predictive science series time series time series forecasting type