Update README.md
Browse files
README.md
CHANGED
|
@@ -9,12 +9,12 @@ tags:
|
|
| 9 |
|
| 10 |
# Kronos: A Foundation Model for the Language of Financial Markets
|
| 11 |
|
| 12 |
-
[](https://
|
| 13 |
[](https://shiyu-coder.github.io/Kronos-demo/)
|
| 14 |
[](https://github.com/shiyu-coder/Kronos)
|
| 15 |
|
| 16 |
<p align="center">
|
| 17 |
-
<img src="https://github.com/shiyu-coder/Kronos/
|
| 18 |
</p>
|
| 19 |
|
| 20 |
**Kronos** is the **first open-source foundation model** for financial candlesticks (K-lines), trained on data from over **45 global exchanges**. It is designed to handle the unique, high-noise characteristics of financial data.
|
|
@@ -26,7 +26,7 @@ Kronos is a family of decoder-only foundation models, pre-trained specifically f
|
|
| 26 |
2. A large, autoregressive Transformer is then pre-trained on these tokens, enabling it to serve as a unified model for diverse quantitative tasks.
|
| 27 |
|
| 28 |
<p align="center">
|
| 29 |
-
<img src="https://github.com/shiyu-coder/Kronos/
|
| 30 |
</p>
|
| 31 |
|
| 32 |
The success of large-scale pre-training paradigm, exemplified by Large Language Models (LLMs), has inspired the development of Time Series Foundation Models (TSFMs). Kronos addresses existing limitations by introducing 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, including price series forecasting, volatility forecasting, and synthetic data generation.
|
|
@@ -138,7 +138,7 @@ For a complete, runnable script that includes data loading, prediction, and plot
|
|
| 138 |
Running this script will generate a plot comparing the ground truth data against the model's forecast, similar to the one shown below:
|
| 139 |
|
| 140 |
<p align="center">
|
| 141 |
-
<img src="https://github.com/shiyu-coder/Kronos/
|
| 142 |
</p>
|
| 143 |
|
| 144 |
Additionally, a script that makes predictions without Volume and Amount data can be found in [`examples/prediction_wo_vol_example.py`](https://github.com/shiyu-coder/Kronos/blob/main/examples/prediction_wo_vol_example.py).
|
|
|
|
| 9 |
|
| 10 |
# Kronos: A Foundation Model for the Language of Financial Markets
|
| 11 |
|
| 12 |
+
[](https://arxiv.org/abs/2508.02739)
|
| 13 |
[](https://shiyu-coder.github.io/Kronos-demo/)
|
| 14 |
[](https://github.com/shiyu-coder/Kronos)
|
| 15 |
|
| 16 |
<p align="center">
|
| 17 |
+
<img src="https://github.com/shiyu-coder/Kronos/blob/master/figures/logo.jpeg?raw=true" alt="Kronos Logo" width="100">
|
| 18 |
</p>
|
| 19 |
|
| 20 |
**Kronos** is the **first open-source foundation model** for financial candlesticks (K-lines), trained on data from over **45 global exchanges**. It is designed to handle the unique, high-noise characteristics of financial data.
|
|
|
|
| 26 |
2. A large, autoregressive Transformer is then pre-trained on these tokens, enabling it to serve as a unified model for diverse quantitative tasks.
|
| 27 |
|
| 28 |
<p align="center">
|
| 29 |
+
<img src="https://github.com/shiyu-coder/Kronos/blob/master/figures/overview.png?raw=true" alt="Kronos Overview" align="center" width="700px" />
|
| 30 |
</p>
|
| 31 |
|
| 32 |
The success of large-scale pre-training paradigm, exemplified by Large Language Models (LLMs), has inspired the development of Time Series Foundation Models (TSFMs). Kronos addresses existing limitations by introducing 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, including price series forecasting, volatility forecasting, and synthetic data generation.
|
|
|
|
| 138 |
Running this script will generate a plot comparing the ground truth data against the model's forecast, similar to the one shown below:
|
| 139 |
|
| 140 |
<p align="center">
|
| 141 |
+
<img src="https://github.com/shiyu-coder/Kronos/blob/master/figures/prediction_example.png?raw=true" alt="Forecast Example" align="center" width="600px" />
|
| 142 |
</p>
|
| 143 |
|
| 144 |
Additionally, a script that makes predictions without Volume and Amount data can be found in [`examples/prediction_wo_vol_example.py`](https://github.com/shiyu-coder/Kronos/blob/main/examples/prediction_wo_vol_example.py).
|