O'Doherty, Mairead Maire (2023) Can Textual Data from SEC Filings be used to predict the Directional Movement of Company Stock Price. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (917kB) | Preview |
Preview |
PDF (Configuration manual)
Download (882kB) | Preview |
Abstract
Each year large companies are required to submit written information about their performance to investors. This text data provides an insider view of a companies trajectory and is often the first indication of future success or failure. These filings are large and complex documents, the goal of this work was to test if advancements in Natural Language Processing would enable a decision support tool that would predict the direction the stock price is expected to move in after the filing is published. The Longformer transformer model is tested against a basic XGBoost Classifier model to see if the advanced attention mechanism of the transformer model can capture the complexity of the text data.
Item Type: | Thesis (Masters) |
---|---|
Supervisors: | Name Email Hasanuzzaman, Mohammed UNSPECIFIED |
Subjects: | Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science P Language and Literature > P Philology. Linguistics > Computational linguistics. Natural language processing H Social Sciences > HG Finance > Investment > Stock Exchange |
Divisions: | School of Computing > Master of Science in Data Analytics |
Depositing User: | Tamara Malone |
Date Deposited: | 23 May 2023 15:45 |
Last Modified: | 23 May 2023 15:45 |
URI: | https://norma.ncirl.ie/id/eprint/6627 |
Actions (login required)
View Item |