Options
Leveraging BERT to Improve the FEARS Index for Stock Forecasting
Author(s)
Date Issued
2019-08-12
Date Available
2020-05-05T13:45:10Z
Abstract
Financial and Economic Attitudes Revealed by Search (FEARS) index reflects the attention and sentiment of public investors and is an important factor for predicting stock price return. In this paper, we take into account the semantics of the FEARS search terms by leveraging the Bidirectional Encoder Representations from Transformers (BERT), and further apply a self-attention deep learning model to our refined FEARS seamlessly for stock return prediction. We demonstrate the practical benefits of our approach by comparing to baseline works.
Sponsorship
Science Foundation Ireland
Type of Material
Conference Publication
Publisher
ACL
Copyright (Published Version)
2019 the Authors
Keywords
Web versions
Language
English
Status of Item
Peer reviewed
Conference Details
The First Workshop on Financial Technology and Natural Language Processing, Macao, China, 12 August 2019
This item is made available under a Creative Commons License
File(s)
Owning collection
Views
915
Acquisition Date
Mar 28, 2024
Mar 28, 2024
Downloads
530
Acquisition Date
Mar 28, 2024
Mar 28, 2024