间歇性时间序列预测：局部模型与全局模型
Intermittent time series forecasting: local vs global models
AI总结：
针对间歇性时间序列预测问题，首次系统比较了概率性局部模型与全局模型（如TiDE），发现简单神经网络架构TiDE在精度和计算效率上均优于局部模型，且Tweedie分布头对高分位数估计最佳。
摘要：
预测包含零值的间歇性时间序列是供应链中的一个关键挑战，因为库存策略需要概率预测来建立安全水平。间歇性时间序列通常使用局部模型进行预测，即对每个时间序列单独训练。近年来，基于大量时间序列训练的全局模型在时间序列预测中变得流行。全局模型通常基于神经网络或梯度提升树。我们进行了首次研究，比较了最先进的概率性局部模型和全局模型在间歇性时间序列上的表现。对于全局模型，我们考虑了三种适用于间歇性时间序列的不同分布头：负二项、障碍移位负二项和Tweedie。据我们所知，这是后两者首次与神经网络结合使用。我们在五个数据集上进行了实验，这些数据集总共包含超过40,000个真实世界的时间序列。在全局模型中，TiDE（一种简单的神经网络架构）取得了最佳精度；它还持续优于局部模型，并且计算需求更低。大型全局模型反而计算需求更高且精度更低。在分布头中，Tweedie提供了最高分位数的最佳估计。
英文摘要：
Forecasting intermittent time series, which contain zeros, is a crucial challenge in supply chains as inventory policies require probabilistic forecasts to establish safety levels. Intermittent time series are commonly forecast using local models, trained individually on each time series. In the last years global models, trained on a large collection of time series, have become popular for time series forecasting. Global models are often based on neural networks or gradient boosted trees. We carry out the first study comparing state-of-the-art probabilistic local and global models on intermittent time series. For global models we consider three different distribution heads suitable for intermittent time series: negative binomial, hurdle-shifted negative binomial and Tweedie. To the best of our knowledge, this is the first use of the latter two with neural networks. We perform experiments on five datasets comprising overall more than 40'000 real-world time series. Among global models, TiDE, a simple neural network architecture, achieves the best accuracy; it also consistently outperforms local models and has lower computational requirements. Large global models are instead much more computationally demanding and less accurate. Among the distribution heads, the Tweedie provides the best estimates of the highest quantiles.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
