DANLIP: Deep Autoregressive Networks for Locally Interpretable Probabilistic Forecasting

TL;DR

DANLIP introduces an intrinsically interpretable deep learning model for probabilistic time series forecasting, balancing transparency with competitive accuracy across various datasets.

Contribution

The paper presents a novel deep autoregressive network architecture that is inherently interpretable, addressing the black-box issue in neural time series forecasting.

Findings

DANLIP achieves comparable accuracy to state-of-the-art methods.

Interpreting model parameters yields useful domain insights.

The model performs well across multiple datasets.

Abstract

Despite the high performance of neural network-based time series forecasting methods, the inherent challenge in explaining their predictions has limited their applicability in certain application areas. Due to the difficulty in identifying causal relationships between the input and output of such black-box methods, they rarely have been adopted in domains such as legal and medical fields in which the reliability and interpretability of the results can be essential. In this paper, we propose \model, a novel deep learning-based probabilistic time series forecasting architecture that is intrinsically interpretable. We conduct experiments with multiple datasets and performance metrics and empirically show that our model is not only interpretable but also provides comparable performance to state-of-the-art probabilistic time series forecasting methods. Furthermore, we demonstrate that interpreting the parameters of the stochastic processes of interest can provide useful insights into several application areas.