# Forecasting intermittent time series with Gaussian Processes and Tweedie likelihood

arXiv: https://arxiv.org/abs/2502.19086 · HTML: https://mlsanity.com/paper/2502.19086/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 46 references that are in the map.
- First posted on arXiv 26 Feb 2025.

## Builds on (most cited first, 9 of 9)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networks](https://mlsanity.com/paper/1704.04110/) (2017)
- [GPyTorch: Blackbox Matrix-Matrix Gaussian Process Inference with GPU Acceleration](https://mlsanity.com/paper/1809.11165/) (2018)
- [Gaussian Processes for Big Data](https://mlsanity.com/paper/1309.6835/) (2013)
- [Scalable Variational Gaussian Process Classification](https://mlsanity.com/paper/1411.2005/) (2014)
- [Time series forecasting with Gaussian Processes needs priors](https://mlsanity.com/paper/2009.08102/) (2020)
- [Scalable Probabilistic Forecasting in Retail with Gradient Boosted Trees: A Practitioner's Approach](https://mlsanity.com/paper/2311.00993/) (2023)
- [Effective Bayesian Modeling of Groups of Related Count Time Series](https://mlsanity.com/paper/1405.3738/) (2014)

## Built on by (most cited first, 3 of 3)

- [Intermittent time series forecasting: local vs global models](https://mlsanity.com/paper/2601.14031/) (2026)
- [Model selection with proper scoring rules on data sets of time series: prefer the mean scaled score](https://mlsanity.com/paper/2606.24715/) (2026)
- [fable.intermittent: benchmarking probabilistic forecasting methods for intermittent time series](https://mlsanity.com/paper/2609.28607/) (2026)

## Abstract (arXiv)

We adopt Gaussian Processes (GPs) as latent functions for probabilistic forecasting of intermittent time series. The model is trained in a Bayesian framework that accounts for the uncertainty about the latent function. We couple the latent GP variable with two types of forecast distributions: the negative binomial (NegBinGP) and the Tweedie distribution (TweedieGP). While the negative binomial has already been used in forecasting intermittent time series, this is the first time in which a fully parameterized Tweedie density is used for intermittent time series. We properly evaluate the Tweedie density, which has both a point mass at zero and heavy tails, avoiding simplifying assumptions made in existing models. We test our models on thousands of intermittent count time series. Results show that our models provide consistently better probabilistic forecasts than the competitors. In particular, TweedieGP obtains the best estimates of the highest quantiles, thus showing that it is more flexible than NegBinGP.