Back to the Future: Look-ahead Augmentation and Parallel Self-Refinement for Time Series Forecasting

TL;DR

The paper introduces BTTF, a simple framework that improves long-term time series forecasting by using look-ahead augmentation and self-refinement, achieving significant accuracy gains without complex models.

Contribution

BTTF offers a novel, straightforward approach to enhance forecast stability and accuracy through ensembling and self-correction, bridging the gap between parallel and sequential forecasting methods.

Findings

Achieves up to 58% accuracy improvement in long-horizon forecasts.

Enhances stability of linear models in long-term predictions.

Effective even with suboptimal first-stage models.

Abstract

Long-term time series forecasting (LTSF) remains challenging due to the trade-off between parallel efficiency and sequential modeling of temporal coherence. Direct multi-step forecasting (DMS) methods enable fast, parallel prediction of all future horizons but often lose temporal consistency across steps, while iterative multi-step forecasting (IMS) preserves temporal dependencies at the cost of error accumulation and slow inference. To bridge this gap, we propose Back to the Future (BTTF), a simple yet effective framework that enhances forecasting stability through look-ahead augmentation and self-corrective refinement. Rather than relying on complex model architectures, BTTF revisits the fundamental forecasting process and refines a base model by ensembling the second-stage models augmented with their initial predictions. Despite its simplicity, our approach consistently improves long-horizon accuracy and mitigates the instability of linear forecasting models, achieving accuracy gains of up to 58% and demonstrating stable improvements even when the first-stage model is trained under suboptimal conditions. These results suggest that leveraging model-generated forecasts as augmentation can be a simple yet powerful way to enhance long-term prediction, even without complex architectures.