Spaces:

FinText
/

README

Running

Eghbal commited on Nov 11

Commit

a81f137

verified ·

1 Parent(s): 042d787

Update README.md

Files changed (1) hide show

README.md CHANGED Viewed

@@ -35,7 +35,8 @@ We are pleased to introduce **FinText-TSFM**, a comprehensive suite of **time se
   - U.S.: Covers **U.S.** market-wide excess returns from 2000 to 2023, with one pre-trained model per year.
   - Global: Covers excess returns across **89 global markets** from 2000 to 2023, with one pre-trained model for each year.
   - Augmented: Extends the global data with  **augmented factors** from 2000 to 2023, with one pre-trained model for each year.
-  - The remaining TSFMs are available for download via the [**FinText.ai Portal**](https://fintext.ai).
 - **Performance Insights:**
   Our findings show that **off-the-shelf TSFMs** underperform in zero-shot forecasting, while **finance-pretrained models** achieve large gains in both predictive accuracy and portfolio performance.

   - U.S.: Covers **U.S.** market-wide excess returns from 2000 to 2023, with one pre-trained model per year.
   - Global: Covers excess returns across **89 global markets** from 2000 to 2023, with one pre-trained model for each year.
   - Augmented: Extends the global data with  **augmented factors** from 2000 to 2023, with one pre-trained model for each year.
+  - The remaining **220 pre-trained models** are available for download via the [**FinText.ai Portal**](https://fintext.ai). These include models fine-tuned with varying **hyperparameter configurations** for extended experimentation and performance comparison.
 - **Performance Insights:**
   Our findings show that **off-the-shelf TSFMs** underperform in zero-shot forecasting, while **finance-pretrained models** achieve large gains in both predictive accuracy and portfolio performance.