Intermittent time series forecasting: local vs global models

2026-01-20

AI Summary

Probabilistic forecasting of intermittent time series—characterized by a high frequency of zero values—is crucial yet challenging in supply chain inventory management. This study systematically compares local models (e.g., iETS, TweedieGP) with global neural network approaches (e.g., D-Linear, DeepAR, Transformer) and, for the first time, integrates hurdle-shifted negative binomial and Tweedie distributions as probabilistic output heads for neural networks. Extensive experiments on over 40,000 real-world sequences demonstrate that D-Linear consistently outperforms local models in both predictive accuracy and computational efficiency. Among the proposed distributional heads, the negative binomial formulation yields the best overall performance, while the Tweedie distribution excels specifically in high quantile forecasting.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Reasoning under Uncertainty: Relational Probabilistic Models
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Intermittent time series, characterised by the presence of a significant amount of zeros, constitute a large percentage of inventory items in supply chain. Probabilistic forecasts are needed to plan the inventory levels; the predictive distribution should cover non-negative values, have a mass in zero and a long upper tail. Intermittent time series are commonly forecast using local models, which are trained individually on each time series. In the last years global models, which are trained on a large collection of time series, have become popular for time series forecasting. Global models are often based on neural networks. However, they have not yet been exhaustively tested on intermittent time series. We carry out the first study comparing state-of-the-art local (iETS, TweedieGP) and global models (D-Linear, DeepAR, Transformers) on intermittent time series. For neural networks models we consider three different distribution heads suitable for intermittent time series: negative binomial, hurdle-shifted negative binomial and Tweedie. We use, for the first time, the last two distribution heads with neural networks. We perform experiments on five large datasets comprising more than 40'000 real-world time series. Among neural networks D-Linear provides best accuracy; it also consistently outperforms the local models. Moreover, it has also low computational requirements. Transformers-based architectures are instead much more computationally demanding and less accurate. Among the distribution heads, the Tweedie provides the best estimates of the highest quantiles, while the negative binomial offers overall the best performance.

Problem

• intermittent time series
• probabilistic forecasting
• inventory planning
• zero-inflated data
• time series forecasting

Innovation

• intermittent time series
• global models
• distribution heads
• D-Linear
• probabilistic forecasting