N-HiTS: Neural Hierarchical Interpolation for Time Series Forecasting

TL;DR

N-HiTS introduces a hierarchical interpolation approach with multi-rate sampling to improve long-horizon time series forecasting, achieving higher accuracy and significantly reduced computation time compared to existing methods.

Contribution

The paper presents N-HiTS, a novel neural forecasting model that effectively handles long horizons through hierarchical interpolation and multi-rate data sampling techniques.

Findings

Achieves nearly 20% accuracy improvement over Transformer models.

Reduces computation time by approximately 50 times.

Demonstrates effectiveness on large-scale long-horizon datasets.

Abstract

Recent progress in neural forecasting accelerated improvements in the performance of large-scale forecasting systems. Yet, long-horizon forecasting remains a very difficult task. Two common challenges afflicting the task are the volatility of the predictions and their computational complexity. We introduce N-HiTS, a model which addresses both challenges by incorporating novel hierarchical interpolation and multi-rate data sampling techniques. These techniques enable the proposed method to assemble its predictions sequentially, emphasizing components with different frequencies and scales while decomposing the input signal and synthesizing the forecast. We prove that the hierarchical interpolation technique can efficiently approximate arbitrarily long horizons in the presence of smoothness. Additionally, we conduct extensive large-scale dataset experiments from the long-horizon forecasting literature, demonstrating the advantages of our method over the state-of-the-art methods, where N-HiTS provides an average accuracy improvement of almost 20% over the latest Transformer architectures while reducing the computation time by an order of magnitude (50 times). Our code is available at bit.ly/3VA5DoT