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