Scholarlink

<p>Recent work for time-series forecasting increasingly leverages the high predictive power of Deep Learning models. With this increase in model complexity, however, comes a lack in understanding of the underlying model decision process, which is problematic for safety-critical application scenarios. At the same time, simple, interpretable forecasting methods such as ARIMA and ETS still perform very well, sometimes on-par with Deep Learning approaches. We argue that using interpretable forecasters leads to good predictions in most cases. However, the forecasting performance can be improved by selecting a Deep Learning method only for few, important predictions, increasing the overall interpretability of the forecasting process. In this context, we propose a novel online model selection framework which learns to identify these predictions. An extensive empirical study on various real-world datasets containing over 3500 individual time-series shows that our selection methodology performs comparable to state-of-the-art online model selection methods in most cases while being significantly more interpretable. We find that almost always choosing a simple autoregressive or exponential smoothing model for forecasting, results in competitive performance, suggesting that the need for opaque black-box models in time-series forecasting might be smaller than recent works would suggest.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

AALF: Almost Always Linear Forecasting

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年3月6日

查看全文
  • Matthias Jakobs,
  • Thomas Liebig

摘要

Recent work for time-series forecasting increasingly leverages the high predictive power of Deep Learning models. With this increase in model complexity, however, comes a lack in understanding of the underlying model decision process, which is problematic for safety-critical application scenarios. At the same time, simple, interpretable forecasting methods such as ARIMA and ETS still perform very well, sometimes on-par with Deep Learning approaches. We argue that using interpretable forecasters leads to good predictions in most cases. However, the forecasting performance can be improved by selecting a Deep Learning method only for few, important predictions, increasing the overall interpretability of the forecasting process. In this context, we propose a novel online model selection framework which learns to identify these predictions. An extensive empirical study on various real-world datasets containing over 3500 individual time-series shows that our selection methodology performs comparable to state-of-the-art online model selection methods in most cases while being significantly more interpretable. We find that almost always choosing a simple autoregressive or exponential smoothing model for forecasting, results in competitive performance, suggesting that the need for opaque black-box models in time-series forecasting might be smaller than recent works would suggest.