Saved in:
Bibliographic Details
Main Authors: Kim, Sunho, Yoon, Susik
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.02146
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915768819515392
author Kim, Sunho
Yoon, Susik
author_facet Kim, Sunho
Yoon, Susik
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2602_02146
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Back to the Future: Look-ahead Augmentation and Parallel Self-Refinement for Time Series Forecasting
Kim, Sunho
Yoon, Susik
Machine Learning
Artificial Intelligence
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.
title Back to the Future: Look-ahead Augmentation and Parallel Self-Refinement for Time Series Forecasting
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2602.02146