2024/09/26 by Daan Caljon, Jeff Vercauteren, Caljon, Daan +7 · 1 citation
Computer Science · Decision Sciences · Mathematics · #FOS: Computer and information sciences #Forecasting Techniques and Applications #Machine Learning (cs.LG) #Machine Learning (stat.ML) #cs.LG #stat.ML
paper · pdf · doi:10.48550/arxiv.2409.18267
openalex publication_date 2024/09/26 · arxiv created 2025/01/20 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28 · arxiv updated 2026/08/04
Rolling origin forecast instability refers to variability in forecasts for a specific period induced by updating the forecast when new data points become available. Recently, an extension to the N-BEATS model for univariate time series point forecasting was proposed to include forecast stability as an additional optimization objective, next to accuracy. It was shown that more stable forecasts can be obtained without harming accuracy by minimizing a composite loss function that contains both a forecast error and a forecast instability component, with a static hyperparameter to control the impact of stability. In this paper, we empirically investigate whether further improvements in stability can be obtained without compromising accuracy by applying dynamic loss weighting algorithms, which change the loss weights during training. We show that existing dynamic loss weighting methods can achieve this objective and provide insights into why this might be the case. Additionally, we propose an extension to the Random Weighting approach -- Task-Aware Random Weighting -- which also achieves this objective.