Time Series Forecasting
TimesFM
masanorihirano commited on
Commit
637e1de
1 Parent(s): 4697fe9

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +34 -3
README.md CHANGED
@@ -1,3 +1,34 @@
1
- ---
2
- license: cc-by-nc-sa-4.0
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-nc-sa-4.0
3
+ library_name: timesfm
4
+ pipeline_tag: time-series-forecasting
5
+ ---
6
+
7
+ # TimesFM_fin
8
+
9
+ [TimesFM](https://github.com/google-research/timesfm) is a time series foundation model released by Google in 2024.
10
+ TimesFM_fin is a financial-tuned TimesFM trained in this [work](https://tech.preferred.jp/en/).
11
+
12
+ **Resources and Technical Documentation**:
13
+
14
+ * Paper: TBD
15
+ * [Our Tech Blog](https://tech.preferred.jp/en/)
16
+ * [GitHub repo](https://github.com/pfnet-research/timesfm_fin)
17
+
18
+ **Authors**:
19
+ - Xinghong Fu
20
+ - Masanori Hirano
21
+ - Kentaro Imajo
22
+
23
+ ## Installation & Usages
24
+ See our [GitHub repo](https://github.com/pfnet-research/timesfm_fin)
25
+
26
+ ## Bias, Risks, and Limitations
27
+ TimesFM_fin is a new technology that carries risks with use.
28
+ Testing conducted to date has not covered, nor could it cover all scenarios.
29
+ 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.
30
+ This model is not designed for legal, tax, investment, financial, or other advice.
31
+ Therefore, before deploying any applications of TimesFM_fin, developers should perform safety testing and tuning tailored to their specific applications of the model.
32
+
33
+ ## License
34
+ CC BY-NC-SA 4.0