Align outputs to improve long-term time series forecasting accuracy
AliO: Output Alignment Matters in Long-Term Time Series Forecasing
Artificial Intelligence
Summary
When predicting future events based on past data, it's important for the model's predictions at the same future time to match up well, but current models often give conflicting answers. The authors introduce AliO, a method that makes these predictions more consistent by aligning their outputs better. They also created a new way to measure how well predictions align over time. Their tests show AliO can make forecasts more reliable without losing accuracy.
What this means in practice
- •For weather forecasters: Create more consistent and reliable weather predictions for the same future times using time series forecasting models with aligned outputs.
- •For energy consumption planners: Improve forecasting reliability of electricity usage patterns to better plan supply and demand over long periods.
Authors
Kwangryeol Park, Jaeho Kim, Seulki Lee
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.