corresponding code to the paper:https://arxiv.org/abs/2502.14897

- Neptune AI results for language model experiments can be found[here](https://app.neptune.ai/o/Financial-NLP/org/market-aware-embedding/) including tables, confusion matrixes and more.

- the main notebook on Kaggle called tweet-classification can be found[here](https://github.com/hamidm21/Revisit_FSA/blob/master/notebook/tweet-classification.ipynb)

- the final implementation and optimization of Triple Barrier Labeling can be found in the notebook[next_day_prediction](https://github.com/hamidm21/Revisit_FSA/blob/master/notebook/next_day_prediction.ipynb)

<imgsrc="https://github.com/user-attachments/assets/effe54e0-2419-411b-bd8c-b65891690d1d"alt="Triple Barrier Labeling"width="300"height="300">

- backtesting experiments and results can be found[here](https://github.com/hamidm21/Revisit_FSA/blob/master/notebook/backtest.ipynb)

use poetry to install the packages with```poetry install```. for more information go to poetry[docs](https://python-poetry.org/docs/basic-usage/)

Here are the folders and what they contain:

- raw: unprocessed data

- dataset: processed data

- notebook:source codes

- notebook:notebooks

- src: contains the source code for experiments