|
--- |
|
license: cc-by-nc-sa-4.0 |
|
library_name: timesfm |
|
pipeline_tag: time-series-forecasting |
|
--- |
|
|
|
# TimesFM_fin |
|
|
|
[TimesFM](https://github.com/google-research/timesfm) is a time series foundation model released by Google in 2024. |
|
TimesFM_fin is a financial-tuned TimesFM trained in this [work](https://tech.preferred.jp/en/). |
|
|
|
**Resources and Technical Documentation**: |
|
|
|
* Paper: TBD |
|
* [Our Tech Blog](https://tech.preferred.jp/en/) |
|
* [GitHub repo](https://github.com/pfnet-research/timesfm_fin) |
|
|
|
**Authors**: |
|
- Xinghong Fu |
|
- Masanori Hirano |
|
- Kentaro Imajo |
|
|
|
## Installation & Usages |
|
See our [GitHub repo](https://github.com/pfnet-research/timesfm_fin) |
|
|
|
## Bias, Risks, and Limitations |
|
TimesFM_fin is a new technology that carries risks with use. |
|
Testing conducted to date has not covered, nor could it cover all scenarios. |
|
For these reasons, TimesFM_fin’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses. |
|
This model is not designed for legal, tax, investment, financial, or other advice. |
|
Therefore, before deploying any applications of TimesFM_fin, developers should perform safety testing and tuning tailored to their specific applications of the model. |
|
|
|
## License |
|
CC BY-NC-SA 4.0 |
|
|
