README.md

---
license: mit
pipeline_tag: time-series-forecasting
tags:
- Finance
- Candlestick
- K-line
library_name: Kronos
---

# Kronos: A Foundation Model for the Language of Financial Markets

Kronos is the **first open-source foundation model** for financial candlesticks (K-lines), trained on data from over **45 global exchanges**. It was presented in the paper [Kronos: A Foundation Model for the Language of Financial Markets](https://huggingface.co/papers/2508.02739).

For full details, including the complete codebase and additional examples, please visit our [GitHub page](https://github.com/shiyu-coder/Kronos).

Try out our live demo showcasing Kronos's forecasting results for the BTC/USDT trading pair: [Access the Live Demo Here](https://shiyu-coder.github.io/Kronos-demo/)

<p align="center">
    <img src="https://github.com/shiyu-coder/Kronos/raw/main/figures/overview.png" alt="Kronos Overview" width="700px" />
</p>

## Abstract
The success of large-scale pre-training paradigm, exemplified by Large Language Models (LLMs), has inspired the development of Time Series Foundation Models (TSFMs). However, their application to financial candlestick (K-line) data remains limited, often underperforming non-pre-trained architectures. Moreover, existing TSFMs often overlook crucial downstream tasks such as volatility prediction and synthetic data generation. To address these limitations, we propose Kronos, a unified, scalable pre-training framework tailored to financial K-line modeling. Kronos introduces a specialized tokenizer that discretizes continuous market information into token sequences, preserving both price dynamics and trade activity patterns. We pre-train Kronos using an autoregressive objective on a massive, multi-market corpus of over 12 billion K-line records from 45 global exchanges, enabling it to learn nuanced temporal and cross-asset representations. Kronos excels in a zero-shot setting across a diverse set of financial tasks. On benchmark datasets, Kronos boosts price series forecasting RankIC by 93% over the leading TSFM and 87% over the best non-pre-trained baseline. It also achieves a 9% lower MAE in volatility forecasting and a 22% improvement in generative fidelity for synthetic K-line sequences. These results establish Kronos as a robust, versatile foundation model for end-to-end financial time series analysis. Our pre-trained model is publicly available at this https URL.

## Model Zoo
We release a family of pre-trained models with varying capacities to suit different computational and application needs. All models are readily accessible from the Hugging Face Hub.

| Model        | Tokenizer                                                                       | Context length | Param  | Open-source                                                               |
|--------------|---------------------------------------------------------------------------------| -------------- | ------ |---------------------------------------------------------------------------|
| Kronos-mini  | [Kronos-Tokenizer-2k](https://huggingface.co/NeoQuasar/Kronos-Tokenizer-2k)     | 2048           | 4.1M   | ✅ [NeoQuasar/Kronos-mini](https://huggingface.co/NeoQuasar/Kronos-mini)  |
| Kronos-small | [Kronos-Tokenizer-base](https://huggingface.co/NeoQuasar/Kronos-Tokenizer-base) | 512            | 24.7M  | ✅ [NeoQuasar/Kronos-small](https://huggingface.co/NeoQuasar/Kronos-small) |
| Kronos-base  | [Kronos-Tokenizer-base](https://huggingface.co/NeoQuasar/Kronos-Tokenizer-base) | 512            | 102.3M | ✅ [NeoQuasar/Kronos-base](https://huggingface.co/NeoQuasar/Kronos-base)   |
| Kronos-large | [Kronos-Tokenizer-base](https://huggingface.co/NeoQuasar/Kronos-Tokenizer-base) | 512            | 499.2M | ❌                                                                         |

## Getting Started

### Installation
1. Install Python 3.10+, and then install the dependencies:

```shell
pip install -r requirements.txt
```

### Making Forecasts
Forecasting with Kronos is straightforward using the `KronosPredictor` class. It handles data preprocessing, normalization, prediction, and inverse normalization, allowing you to get from raw data to forecasts in just a few lines of code.

**Important Note**: The `max_context` for `Kronos-small` and `Kronos-base` is **512**. This is the maximum sequence length the model can process. For optimal performance, it is recommended that your input data length (i.e., `lookback`) does not exceed this limit. The `KronosPredictor` will automatically handle truncation for longer contexts.

Here is a step-by-step guide to making your first forecast.

#### 1. Load the Tokenizer and Model
First, load a pre-trained Kronos model and its corresponding tokenizer from the Hugging Face Hub.

```python
from model import Kronos, KronosTokenizer, KronosPredictor

# Load from Hugging Face Hub
tokenizer = KronosTokenizer.from_pretrained("NeoQuasar/Kronos-Tokenizer-base")
model = Kronos.from_pretrained("NeoQuasar/Kronos-small")
```

#### 2. Instantiate the Predictor
Create an instance of `KronosPredictor`, passing the model, tokenizer, and desired device.

```python
# Initialize the predictor
predictor = KronosPredictor(model, tokenizer, device="cuda:0", max_context=512)
```

#### 3. Prepare Input Data
The `predict` method requires three main inputs:
-   `df`: A pandas DataFrame containing the historical K-line data. It must include columns `['open', 'high', 'low', 'close']`. `volume` and `amount` are optional.
-   `x_timestamp`: A pandas Series of timestamps corresponding to the historical data in `df`.
-   `y_timestamp`: A pandas Series of timestamps for the future periods you want to predict.

```python
import pandas as pd

# Load your data
df = pd.read_csv("./data/XSHG_5min_600977.csv")
df['timestamps'] = pd.to_datetime(df['timestamps'])

# Define context window and prediction length
lookback = 400
pred_len = 120

# Prepare inputs for the predictor
x_df = df.loc[:lookback-1, ['open', 'high', 'low', 'close', 'volume', 'amount']]
x_timestamp = df.loc[:lookback-1, 'timestamps']
y_timestamp = df.loc[lookback:lookback+pred_len-1, 'timestamps']
```

#### 4. Generate Forecasts
Call the `predict` method to generate forecasts. You can control the sampling process with parameters like `T`, `top_p`, and `sample_count` for probabilistic forecasting.

```python
# Generate predictions
pred_df = predictor.predict(
    df=x_df,
    x_timestamp=x_timestamp,
    y_timestamp=y_timestamp,
    pred_len=pred_len,
    T=1.0,          # Temperature for sampling
    top_p=0.9,      # Nucleus sampling probability
    sample_count=1  # Number of forecast paths to generate and average
)

print("Forecasted Data Head:")
print(pred_df.head())
```

The `predict` method returns a pandas DataFrame containing the forecasted values for `open`, `high`, `low`, `close`, `volume`, and `amount`, indexed by the `y_timestamp` you provided.

#### 5. Example and Visualization
For a complete, runnable script that includes data loading, prediction, and plotting, please see [`examples/prediction_example.py`](https://github.com/shiyu-coder/Kronos/blob/main/examples/prediction_example.py).

Running this script will generate a plot comparing the ground truth data against the model's forecast, similar to the one shown below:

<p align="center">
    <img src="https://github.com/shiyu-coder/Kronos/raw/main/figures/prediction_example.png" alt="Forecast Example" width="600px" />
</p>

Additionally, we also provide a script that makes predictions without Volume and Amount data, which can be found in [`examples/prediction_wo_vol_example.py`](https://github.com/shiyu-coder/Kronos/blob/main/examples/prediction_wo_vol_example.py).

## Citation
If you use Kronos in your research, we would appreciate a citation to our [paper](https://huggingface.co/papers/2508.02739):

```bibtex
@misc{shi2025kronos,
      title={Kronos: A Foundation Model for the Language of Financial Markets},
      author={Yu Shi and Zongliang Fu and Shuo Chen and Bohan Zhao and Wei Xu and Changshui Zhang and Jian Li},
      year={2025},
      eprint={2508.02739},
      archivePrefix={arXiv},
      primaryClass={q-fin.ST},
      url={https://arxiv.org/abs/2508.02739},
}
```