Chronos: Learning the Language of Time Series

By Abdul Fatir Ansari, Lorenzo Stella, Caner Turkmen, Xiyuan Zhang, Pedro Mercado, Huibin Shen, Oleksandr Shchur, Syama Sundar Rangapuram, Sebastian Pineda Arango, Shubham Kapoor and 7 more. Trans. Mach. Learn. Res., 2024

878 citations recorded by the source corpus.

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 datasets, relative to methods that were trained specifically on them. Our results demonstrate that Chronos models can leverage time series data from diverse domains to improve zero-shot accuracy on unseen forecasting tasks, positioning pretrained models as a viable tool to greatly simplify forecasting pipelines.

Subfields: Artificial Intelligence, Astronomy and Astrophysics, Signal Processing

View Paper: https://www.semanticscholar.org/paper/02fa77e4f355198cb4270f6d4a07517bf09c46dd

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Artur Dubrawski
2. Mononito Goswami
3. Konrad Szafer
4. Yifu Cai
5. Arjun Choudhry
6. Shuo Li

In Signal Processing

1. Artur Dubrawski

Citations in the corpus

• Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts (2024, neutral): “Recent advancements have facilitated the collection of numerous time series datasets from various sources (Godahewa et al., 2021; Ansari et al., 2024; Woo et al., 2024; Liu et al., 2024d;a).”
• Foundation Models for Time Series Analysis: A Tutorial and Survey (2024, neutral): “Ansari et al. [1] analyze the applicability of the encoder-decoder framework to decoder-only models.”
• MOMENT: A Family of Open Time-series Foundation Models (2024, background): “Two interesting directions include using augmentation and synthetic data (Ansari et al., 2024) to improve the quality of pre-training, and looking at tuning dataset mixtures in the Time Series Pile.”
• Giving Sensors a Voice: Multimodal JEPA for Semantic Time-Series Embeddings (2026, unknown): “Early foundational attempts predominantly addressed univariate series (Das et al., 2024; Ansari et al., 2024), though recent advancements have successfully extended to multivariate settings with sophisticated cross-channel modeling techniques (Woo et al., 2024b; Liu et al., 2024).”
• TRACE: Grounding Time Series in Context for Multimodal Embedding and Retrieval (2025, unknown): “Chronos [32] tokenizes time series via scaling and quantization, and trains a T5-style model for zero-shot probabilistic forecasting.”
• Time to Embed: Unlocking Foundation Models for Time Series with Channel Descriptions (2025, unknown): “Early foundational attempts predominantly addressed univariate series (Das et al., 2024; Ansari et al., 2024), though recent advancements have successfully extended to multivariate settings with sophisticated cross-channel modeling techniques (Woo et al., 2024; Liu et al., 2024).”