HTML: Hierarchical Transformer-based Multi-task Learning for Volatility Prediction

Files in This Item:
File Description SizeFormat 
insight_publication.pdf1.58 MBAdobe PDFDownload
Title: HTML: Hierarchical Transformer-based Multi-task Learning for Volatility Prediction
Authors: Yang, LinyiNg, Tin Lok JamesSmyth, BarryDong, Ruihai
Permanent link: http://hdl.handle.net/10197/11935
Date: 24-Apr-2020
Online since: 2021-02-09T10:02:26Z
Abstract: Thevolatility forecastingtask refers to predicting the amount ofvariability in the price of a financial asset over a certain period.It is an important mechanism for evaluating the risk associatedwith an asset and, as such, is of significant theoretical and practicalimportance in financial analysis. While classical approaches haveframed this task as a time-series prediction one – using historicalpricing as a guide to future risk forecasting – recent advances innatural language processing have seen researchers turn to com-plementary sources of data, such as analyst reports, social media,and even the audio data from earnings calls. This paper proposes anovel hierarchical, transformer, multi-task architecture designedto harness the text and audio data from quarterly earnings confer-ence calls to predict future price volatility in the short and longterm. This includes a comprehensive comparison to a variety ofbaselines, which demonstrates very significant improvements inprediction accuracy, in the range 17% - 49% compared to the currentstate-of-the-art. In addition, we describe the results of an ablationstudy to evaluate the relative contributions of each component ofour approach and the relative contributions of text and audio datawith respect to prediction accuracy.
Funding Details: Science Foundation Ireland
Funding Details: Insight Research Centre
Type of material: Conference Publication
Publisher: ACM
Copyright (published version): 2020 International World Wide Web Conference Committee
Keywords: Recommender systemsVolatility forecastingHierarchical transformerMulti-task learning
DOI: 10.1145/3366423.3380128
Other versions: https://www2020.thewebconf.org/
Language: en
Status of Item: Peer reviewed
Is part of: Huang, Y., King, I., liu, TY., van Steen, M. WWW'20: Proceedings of The Web Conference 2020
Conference Details: The World Wide Web Conference 2020 (WWW'20), Taipei, Taiwan (held online due to coronavirus outbreak), 20-24 April 2020
ISBN: 978-1-4503-7023-3/20/04
This item is made available under a Creative Commons License: https://creativecommons.org/licenses/by/3.0/ie/
Appears in Collections:Insight Research Collection

Show full item record

Page view(s)

34
checked on Feb 25, 2021

Download(s)

12
checked on Feb 25, 2021

Google ScholarTM

Check

Altmetric


If you are a publisher or author and have copyright concerns for any item, please email research.repository@ucd.ie and the item will be withdrawn immediately. The author or person responsible for depositing the article will be contacted within one business day.