DeepBooTS: Dual-Stream Residual Boosting for Drift-Resilient Time-Series Forecasting

TL;DR

DeepBooTS introduces a dual-stream residual boosting approach that enhances time-series forecasting robustness to concept drift by progressively reconstructing signals through ensemble-based residual correction, outperforming existing methods.

Contribution

It proposes a novel end-to-end dual-stream residual boosting method that improves robustness to concept drift and enhances interpretability in time-series forecasting.

Findings

Outperforms existing methods with an average of 15.8% performance improvement.

Establishes a new benchmark for time-series forecasting.

Demonstrates robustness across large-scale datasets.

Abstract

Time-Series (TS) exhibits pronounced non-stationarity. Consequently, most forecasting methods display compromised robustness to concept drift, despite the prevalent application of instance normalization. We tackle this challenge by first analysing concept drift through a bias-variance lens and proving that weighted ensemble reduces variance without increasing bias. These insights motivate DeepBooTS, a novel end-to-end dual-stream residual-decreasing boosting method that progressively reconstructs the intrinsic signal. In our design, each block of a deep model becomes an ensemble of learners with an auxiliary output branch forming a highway to the final prediction. The block-wise outputs correct the residuals of previous blocks, leading to a learning-driven decomposition of both inputs and targets. This method enhances versatility and interpretability while substantially improving robustness to concept drift. Extensive experiments, including those on large-scale datasets, show that the proposed method outperforms existing methods by a large margin, yielding an average performance improvement of 15.8% across various datasets, establishing a new benchmark for TS forecasting.