# The DeepCAR Method: Forecasting Time-Series Data That Have Change Points

arXiv: https://arxiv.org/abs/2302.11241 · HTML: https://mlsanity.com/paper/2302.11241/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 23 references that are in the map.
- First posted on arXiv 22 Feb 2023.

## Builds on (most cited first, 11 of 11)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networks](https://mlsanity.com/paper/1704.04110/) (2017)
- [Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecasting](https://mlsanity.com/paper/1912.09363/) (2019)
- [Generating Sequences With Recurrent Neural Networks](https://mlsanity.com/paper/1308.0850/) (2013)
- [GluonTS: Probabilistic Time Series Models in Python](https://mlsanity.com/paper/1906.05264/) (2019)
- [On Optimal Multiple Changepoint Algorithms for Large Data](https://mlsanity.com/paper/1409.1842/) (2014)
- [Activation Functions in Artificial Neural Networks: A Systematic Overview](https://mlsanity.com/paper/2101.09957/) (2021)
- [Automatic Change-Point Detection in Time Series via Deep Learning](https://mlsanity.com/paper/2211.03860/) (2022)
- [Online Detection Of Supply Chain Network Disruptions Using Sequential Change-Point Detection for Hawkes Processes](https://mlsanity.com/paper/2211.12091/) (2022)
- [EM's Convergence in Gaussian Latent Tree Models](https://mlsanity.com/paper/2211.11904/) (2022)

## Abstract (arXiv)

Many methods for time-series forecasting are known in classical statistics, such as autoregression, moving averages, and exponential smoothing. The DeepAR framework is a novel, recent approach for time-series forecasting based on deep learning. DeepAR has shown very promising results already. However, time series often have change points, which can degrade the DeepAR's prediction performance substantially. This paper extends the DeepAR framework by detecting and including those change points. We show that our method performs as well as standard DeepAR when there are no change points and considerably better when there are change points. More generally, we show that the batch size provides an effective and surprisingly simple way to deal with change points in DeepAR, Transformers, and other modern forecasting models.