N-BEATS: Neural basis expansion analysis for interpretable time series forecasting

Abstract

We focus on solving the univariate times series point forecasting problem using deep learning. We propose a deep neural architecture based on backward and forward residual links and a very deep stack of fully-connected layers. The architecture has a number of desirable properties, being interpretable, applicable without modification to a wide array of target domains, and fast to train. We test the proposed architecture on several well-known datasets, including M3, M4 and TOURISM competition datasets containing time series from diverse domains. We demonstrate state-of-the-art performance for two configurations of N-BEATS for all the datasets, improving forecast accuracy by 11% over a statistical benchmark and by 3% over last year's winner of the M4 competition, a domain-adjusted hand-crafted hybrid between neural network and statistical time series models. The first configuration of our model does not employ any time-series-specific components and its performance on heterogeneous datasets strongly suggests that, contrarily to received wisdom, deep learning primitives such as residual blocks are by themselves sufficient to solve a wide range of forecasting problems. Finally, we demonstrate how the proposed architecture can be augmented to provide outputs that are interpretable without considerable loss in accuracy.

References in corpus (2)

• A Dual-Stage Attention-Based Recurrent Neural Network for Time Series Prediction
• Deep Factors for Forecasting

Cited by in corpus (13)

• Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting
• Ensembles of Localised Models for Time Series Forecasting
• Hierarchical forecasting with a top-down alignment of independent level forecasts
• A Multi-Variate Triple-Regression Forecasting Algorithm for Long-Term Customized Allergy Season Prediction
• LSTMs and Deep Residual Networks for Carbohydrate and Bolus Recommendations in Type 1 Diabetes Management
• HINNPerf: Hierarchical Interaction Neural Network for Performance Prediction of Configurable Systems
• Interpretable Anomaly Detection with DIFFI: Depth-based Isolation Forest Feature Importance
• Epidemic-guided deep learning for spatiotemporal forecasting of Tuberculosis outbreak
• Agnostic Learning for Packing Machine Stoppage Prediction in Smart Factories
• Multivariate Boosted Trees and Applications to Forecasting and Control
• A projected nonlinear state-space model for forecasting time series signals
• Using dynamic loss weighting to boost improvements in forecast stability
• Meta-Learning for Koopman Spectral Analysis with Short Time-series