Chronos: Learning the Language of Time Series
Abdul Fatir Ansari, Lorenzo Stella, Caner Turkmen, Xiyuan Zhang, Pedro, Mercado, Huibin Shen, Oleksandr Shchur, Syama Sundar Rangapuram, Sebastian, Pineda Arango, Shubham Kapoor, Jasper Zschiegner, Danielle C. Maddix, Hao, Wang, Michael W. Mahoney, Kari Torkkola

TL;DR
Chronos introduces a transformer-based framework that tokenizes and pretrains on diverse time series data, achieving superior zero-shot forecasting performance and simplifying the forecasting process.
Contribution
It presents a novel pretrained probabilistic time series model using tokenization and transformer architectures, demonstrating strong zero-shot capabilities across multiple datasets.
Findings
Outperforms existing methods on training datasets.
Achieves comparable or better zero-shot performance on unseen datasets.
Pretraining improves generalization across diverse time series domains.
Abstract
We introduce Chronos, a simple yet effective framework for pretrained probabilistic time series models. Chronos tokenizes time series values using scaling and quantization into a fixed vocabulary and trains existing transformer-based language model architectures on these tokenized time series via the cross-entropy loss. We pretrained Chronos models based on the T5 family (ranging from 20M to 710M parameters) on a large collection of publicly available datasets, complemented by a synthetic dataset that we generated via Gaussian processes to improve generalization. In a comprehensive benchmark consisting of 42 datasets, and comprising both classical local models and deep learning methods, we show that Chronos models: (a) significantly outperform other methods on datasets that were part of the training corpus; and (b) have comparable and occasionally superior zero-shot performance on new…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
- 🤗amazon/chronos-2model· 10.7M dl· ♡ 21510.7M dl♡ 215
- 🤗autogluon/chronos-bolt-smallmodel· 10.3M dl· ♡ 2710.3M dl♡ 27
- 🤗amazon/chronos-bolt-basemodel· 6.7M dl· ♡ 816.7M dl♡ 81
- 🤗thuml/sundial-base-128mmodel· 1.5M dl· ♡ 751.5M dl♡ 75
- 🤗autogluon/chronos-2model· 8.7M dl· ♡ 68.7M dl♡ 6
- 🤗Salesforce/moirai-2.0-R-smallmodel· 608k dl· ♡ 38608k dl♡ 38
- 🤗ibm-research/patchtst-fm-r1model· 27k dl· ♡ 827k dl♡ 8
- 🤗amazon/chronos-t5-minimodel· 21k dl· ♡ 1921k dl♡ 19
- 🤗amazon/chronos-t5-smallmodel· 1.7M dl· ♡ 1381.7M dl♡ 138
- 🤗amazon/chronos-t5-basemodel· 2.0M dl· ♡ 412.0M dl♡ 41
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsTime Series Analysis and Forecasting · Advanced Text Analysis Techniques · Historical Astronomy and Related Studies
MethodsRefunds@Expedia|||How do I get a full refund from Expedia? · Attention Is All You Need · Byte Pair Encoding · Attention Dropout · Softmax · Gated Linear Unit · Residual Connection · Linear Layer · Dense Connections · SentencePiece
