Downloads · 30 days
2
5% of all-time downloads
NASDAQ_news_binary_headlines_20min
aalindt/NASDAQ_news_binary_headlines_20min
NASDAQ_news_binary_headlines_20min is a text classification model from aalindt. Use it when you need a label for a piece of text. It is set up for transformers.
Model for Binary classification on headlines from the NASDAQnews dataset. Label0 = Downward movement Label1 = Upward movement
All-time downloads
39
Public
Repo size
536 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin268 MB · 100%
At a glance
- Task
- Text Classification
- Library
- transformers
- Model type
- distilbert
- Access
- Public
- Created
- Mar 20, 2023
- Updated
- Mar 20, 2023
- SHA
- 1a7d8467
Try a prompt
Model card
From the Hugging Face model README
Pretrained model used for the NASDAQ_news dataset
Model for Binary classification on headlines from the NASDAQ_news dataset. Label_0 = Downward movement Label_1 = Upward movement
The target_variable is the return 20-minutes after an article has been published
Model Info:
This model is a fine-tuned DistilBertForSequenceClassification on random samples of the NASDAQ_news dataset. It uses the DistilBertTokenizerFast as a tokenizer.
Model Data:
The model is finetuned on headlines
- Task
- Text Classification
- Library
- transformers
- Type
- distilbert
- Languages
- en
- Created
- Mar 20, 2023
- Updated
- Mar 20, 2023