AliO: Output Alignment Matters in Long-Term Time Series Forecasing

2026-10-08

AI Summary

This study addresses the reliability issue in long-term time series forecasting caused by misaligned outputs at identical timestamps. To this end, it pioneers an output alignment perspective and proposes AliO. This method integrates time-frequency domain analysis to impose consistency constraints that reduce temporal and spectral discrepancies, and introduces the TAM metric to quantify alignment degree, thereby overcoming the limitations of conventional approaches that focus solely on prediction error. Experimental results demonstrate that AliO improves TAM by 58.2% and enhances forecasting performance by up to 27.5%, significantly strengthening model reliability.

Abstract

Long-term Time Series Forecasting (LTSF) tasks, which leverage the current data sequence as input to predict the future sequence, have become increasingly crucial in real-world applications such as weather forecasting and planning of electricity consumption. However, state-of-the-art LTSF models often fail to achieve prediction output alignment for the same timestamps across lagged input sequences. Instead, these models exhibit low output alignment, resulting in fluctuation in prediction outputs for the same timestamps, undermining the model's reliability. To address this, we propose AliO (Align Outputs), a novel approach designed to improve the output alignment of LTSF models by reducing the discrepancies between prediction outputs for the same timestamps in both the time and frequency domains. To measure output alignment, we introduce a new metric, TAM (Time Alignment Metric), which quantifies the alignment between prediction outputs, whereas existing metrics such as MSE only capture the distance between prediction outputs and ground truths. Experimental results show that AliO effectively improves the output alignment, i.e., up to 58.2% in TAM, while maintaining or enhancing the forecasting performance (up to 27.5%). This improved output alignment increases the reliability of the LTSF models, making them more applicable in real-world scenarios.

Problem

• Long-term Time Series Forecasting
• Output Alignment
• Reliability
• Prediction Consistency

Innovation

• Long-Term Time Series Forecasting
• Output Alignment
• AliO
• Time Alignment Metric
• Frequency Domain