Neural Additive Models for Nowcasting

TL;DR

This paper introduces a neural additive model tailored for multivariate nowcasting, achieving high prediction accuracy while providing detailed explanations for each input's importance across variables and time steps.

Contribution

The paper proposes a novel NAM approach for multivariate nowcasting that offers interpretability without sacrificing prediction performance.

Findings

NAM-NC predicts as accurately as state-of-the-art neural networks.

NAM-NC provides explanations for input importance across variables and time steps.

Parameter-sharing networks with NAM-NC reduce complexity while maintaining performance.

Abstract

Deep neural networks (DNNs) are one of the most highlighted methods in machine learning. However, as DNNs are black-box models, they lack explanatory power for their predictions. Recently, neural additive models (NAMs) have been proposed to provide this power while maintaining high prediction performance. In this paper, we propose a novel NAM approach for multivariate nowcasting (NC) problems, which comprise an important focus area of machine learning. For the multivariate time-series data used in NC problems, explanations should be considered for every input value to the variables at distinguishable time steps. By employing generalized additive models, the proposed NAM-NC successfully explains each input value's importance for multiple variables and time steps. Experimental results involving a toy example and two real-world datasets show that the NAM-NC predicts multivariate time-series data as accurately as state-of-the-art neural networks, while also providing the explanatory importance of each input value. We also examine parameter-sharing networks using NAM-NC to decrease their complexity, and NAM-MC's hard-tied feature net extracted explanations with good performance.