Intermittent time series forecasting: local vs global models

• URL: http://arxiv.org/abs/2601.14031v1
• Date: Tue, 20 Jan 2026 14:53:24 GMT
• Title: Intermittent time series forecasting: local vs global models
• Authors: Stefano Damato, Nicolò Rubattu, Dario Azzimonti, Giorgio Corani,
• Abstract summary: Intermittent time series characterised by the presence of a significant amount of zeros constitute a large percentage of inventory items in supply chain.<n>Probabilistic forecasts are needed to plan the inventory levels.<n>Intermittent time series are commonly forecast using local models, which are trained individually on each time series.
• Score: 0.13599496385950985
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Breaking Silos: Adaptive Model Fusion Unlocks Better Time Series Forecasting [64.45587649141842]
  Time-series forecasting plays a critical role in many real-world applications.<n>No single model consistently outperforms others across different test samples, but instead (ii) each model excels in specific cases.<n>We introduce TimeFuse, a framework for collective time-series forecasting with sample-level adaptive fusion of heterogeneous models.
  arXiv  Detail & Related papers  (2025-05-24T00:45:07Z)
• Forecasting intermittent time series with Gaussian Processes and Tweedie likelihood [0.14856472820492364]
  We adopt Gaussian Processes (GPs) as latent functions for probabilistic forecasting of intermittent time series.<n>We couple the latent GP variable with two types of forecast distributions: the negative binomial (NegBinGP) and the Tweedie distribution (TweedieGP)
  arXiv  Detail & Related papers  (2025-02-26T12:31:56Z)
• Sundial: A Family of Highly Capable Time Series Foundation Models [47.27032162475962]
  We introduce Sundial, a family of native, flexible, and scalable time series foundation models.<n>Our models are pre-trained without specifying any prior distribution and can generate multiple probable predictions.<n>Sundial achieves state-of-the-art results on both point and probabilistic forecasting benchmarks with a just-in-time inference speed.
  arXiv  Detail & Related papers  (2025-02-02T14:52:50Z)
• No "Zero-Shot" Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performance [68.18779562801762]
  multimodal models require exponentially more data to achieve linear improvements in downstream "zero-shot" performance. Our study reveals an exponential need for training data which implies that the key to "zero-shot" generalization capabilities under large-scale training paradigms remains to be found.
  arXiv  Detail & Related papers  (2024-04-04T17:58:02Z)
• Unified Training of Universal Time Series Forecasting Transformers [104.56318980466742]
  We present a Masked-based Universal Time Series Forecasting Transformer (Moirai) Moirai is trained on our newly introduced Large-scale Open Time Series Archive (LOTSA) featuring over 27B observations across nine domains. Moirai achieves competitive or superior performance as a zero-shot forecaster when compared to full-shot models.
  arXiv  Detail & Related papers  (2024-02-04T20:00:45Z)
• Timer: Generative Pre-trained Transformers Are Large Time Series Models [83.03091523806668]
  This paper aims at the early development of large time series models (LTSM) During pre-training, we curate large-scale datasets with up to 1 billion time points. To meet diverse application needs, we convert forecasting, imputation, and anomaly detection of time series into a unified generative task.
  arXiv  Detail & Related papers  (2024-02-04T06:55:55Z)
• Lag-Llama: Towards Foundation Models for Probabilistic Time Series Forecasting [54.04430089029033]
  We present Lag-Llama, a general-purpose foundation model for time series forecasting based on a decoder-only transformer architecture. Lag-Llama is pretrained on a large corpus of diverse time series data from several domains, and demonstrates strong zero-shot generalization capabilities. When fine-tuned on relatively small fractions of such previously unseen datasets, Lag-Llama achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2023-10-12T12:29:32Z)
• Online Evolutionary Neural Architecture Search for Multivariate Non-Stationary Time Series Forecasting [72.89994745876086]
  This work presents the Online Neuro-Evolution-based Neural Architecture Search (ONE-NAS) algorithm. ONE-NAS is a novel neural architecture search method capable of automatically designing and dynamically training recurrent neural networks (RNNs) for online forecasting tasks. Results demonstrate that ONE-NAS outperforms traditional statistical time series forecasting methods.
  arXiv  Detail & Related papers  (2023-02-20T22:25:47Z)
• STING: Self-attention based Time-series Imputation Networks using GAN [4.052758394413726]
  STING (Self-attention based Time-series Imputation Networks using GAN) is proposed. We take advantage of generative adversarial networks and bidirectional recurrent neural networks to learn latent representations of the time series. Experimental results on three real-world datasets demonstrate that STING outperforms the existing state-of-the-art methods in terms of imputation accuracy.
  arXiv  Detail & Related papers  (2022-09-22T06:06:56Z)
• Networked Time Series Prediction with Incomplete Data [59.45358694862176]
  We propose NETS-ImpGAN, a novel deep learning framework that can be trained on incomplete data with missing values in both history and future. We conduct extensive experiments on three real-world datasets under different missing patterns and missing rates.
  arXiv  Detail & Related papers  (2021-10-05T18:20:42Z)
• Low-Rank Autoregressive Tensor Completion for Multivariate Time Series Forecasting [15.927264813606637]
  Time series collected from sensor networks are often large-scale and incomplete with considerable corruption and missing values. We propose a low-rank autoregressive tensor completion (LATC) framework to model multivariate time series data. Our numerical experiments on three real-world data sets demonstrate the superiority of the integration of global and local trends in LATC.
  arXiv  Detail & Related papers  (2020-06-18T11:31:16Z)
• Zero-shot and few-shot time series forecasting with ordinal regression recurrent neural networks [17.844338213026976]
  Recurrent neural networks (RNNs) are state-of-the-art in several sequential learning tasks, but they often require considerable amounts of data to generalise well. We propose a novel RNN-based model that directly addresses this problem by learning a shared feature embedding over the space of many quantised time series. We show how this enables our RNN framework to accurately and reliably forecast unseen time series, even when there is little to no training data available.
  arXiv  Detail & Related papers  (2020-03-26T21:33:10Z)
• For2For: Learning to forecast from forecasts [1.6752182911522522]
  This paper presents a time series forecasting framework which combines standard forecasting methods and a machine learning model. Tested on the M4 competition dataset, this approach outperforms all submissions for quarterly series, and is more accurate than all but the winning algorithm for monthly series.
  arXiv  Detail & Related papers  (2020-01-14T03:06:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.