Stock2Vec: An Embedding to Improve Predictive Models for Companies

One of 181 items in the title: International Conference on Knowledge Management available on this site.

PDF Version Also Available for Download.

Description

Building predictive models for companies often relies on inference using historical data of companies in the same industry sector. However, companies are similar across a variety of dimensions that should be leveraged in relevant prediction problems. This is particularly true for large, complex organizations which may not be well defined by a single industry and have no clear peers. To enable prediction using company information across a variety of dimensions, we create an embedding of company stocks, Stock2Vec, which can be easily added to any prediction model that applies to companies with associated stock prices. We describe the process of … continued below

Physical Description

14 p. : ill.

Creation Information

Yi, Ziruo; Xiao, Ting; Kaz-Onyeakazi, Ijeoma; Ratnam, Cheran; Medeiros, Theophilus; Nelson, Phillip et al. June 2022.

Context

This text is part of the collection entitled: International Conference on Knowledge Management (ICKM) and was provided by the UNT College of Information to the UNT Digital Library, a digital repository hosted by the UNT Libraries. It has been viewed 108 times. More information about this text can be viewed below.

Who

People and organizations associated with either the creation of this text or its content.

Authors

  • Yi, Ziruo Department of Computer Science and Engineering, University of North Texas, US. Email: ziruoyi@my.unt.edu
  • Xiao, Ting Department of Computer Science and Engineering, University of North Texas and Department of Information Science, University of North Texas, US. Email: ting.xiao@unt.edu
  • Kaz-Onyeakazi, Ijeoma Department of Information Science, University of North Texas, US. Email: ijeomakaz-onyeakazi@my.unt.edu
  • Ratnam, Cheran Department of Information Science, University of North Texas, US. Email: cheran.ratnam@unt.edu
  • Medeiros, Theophilus Department of Computer Science and Engineering, University of North Texas, US. Email: theophilusmedeiros@my.unt.edu
  • Nelson, Phillip Texas Academy of Math and Science, US. Email: phillipnelson@my.unt.edu
  • Baweja, Yuvraj Texas Academy of Math and Science, US. Email: yuvrajbaweja@my.unt.edu

Editor

  • Heisig, Peter University of Applied Sciences - FH Potsdam, Germany. Email: peter.heisig@fh-potsdam.de

Organizer of meeting

Provided By

UNT College of Information

Situated at the intersection of people, technology, and information, the College of Information's faculty, staff and students invest in innovative research, collaborative partnerships, and student-centered education to serve a global information society. The college offers programs of study in information science, learning technologies, and linguistics.

Contact Us

What

Descriptive information to help identify this text. Follow the links below to find similar items on the Digital Library.

Titles

Description

Building predictive models for companies often relies on inference using historical data of companies in the same industry sector. However, companies are similar across a variety of dimensions that should be leveraged in relevant prediction problems. This is particularly true for large, complex organizations which may not be well defined by a single industry and have no clear peers. To enable prediction using company information across a variety of dimensions, we create an embedding of company stocks, Stock2Vec, which can be easily added to any prediction model that applies to companies with associated stock prices. We describe the process of creating this rich vector representation from stock price fluctuations and characterize what the dimensions represent. We then conduct comprehensive experiments to evaluate this embedding in applied machine learning problems in various business contexts. Our experiment results demonstrate that the four features in the Stock2Vec embedding can readily augment existing cross-company models and enhance cross-company predictions.

Physical Description

14 p. : ill.

Notes

The International Conference on Knowledge Management (ICKM) provides researchers and practitioners from all over the world a forum for discussion and exchange of ideas concerning theoretical and practical aspects of Knowledge Management. ICKM 2022 held June 23-24, 2022. in Potsdam, Germany. The conference theme is “Knowledge, Uncertainty and Risks: From Individual to Global Scale” at different levels of analysis.

Source

  • 17th International Conference on Knowledge Management (ICKM-2022), June 23-24, 2022. University of Applied Sciences, Fachhochschule Potsdam, Germany

Language

Item Type

Identifier

Unique identifying numbers for this text in the Digital Library or other systems.

Collections

This text is part of the following collections of related materials.

International Conference on Knowledge Management (ICKM)

Serving as digital proceedings, this collection includes papers, posters, and slides from invited talks as well as practitioner and sponsor presentations for the annual International Conference on Knowledge Management (ICKM).

UNT Scholarly Works

Materials from the UNT community's research, creative, and scholarly activities and UNT's Open Access Repository. Access to some items in this collection may be restricted.

UNT Graduate Student Works

This collection houses graduate student works other than theses and dissertations. All materials have been previously accepted by a professional organization or approved by a faculty mentor. The collection includes, but is not limited to projects or problems in lieu of thesis, supplemental files associated with theses and dissertations, posters, recitals, presentations, articles, reviews, book chapters, exhibitions, and artwork. Some items in this collection are restricted to use by the UNT community.

What responsibilities do I have when using this text?

When

Dates and time periods associated with this text.

Creation Date

  • June 2022

Added to The UNT Digital Library

  • Jan. 26, 2023, 11:14 a.m.

Description Last Updated

  • Nov. 16, 2023, 10:13 a.m.

Usage Statistics

When was this text last used?

Yesterday: 0
Past 30 days: 3
Total Uses: 108

Interact With This Text

Here are some suggestions for what to do next.

Start Reading

PDF Version Also Available for Download.

International Image Interoperability Framework

IIF Logo

We support the IIIF Presentation API

Yi, Ziruo; Xiao, Ting; Kaz-Onyeakazi, Ijeoma; Ratnam, Cheran; Medeiros, Theophilus; Nelson, Phillip et al. Stock2Vec: An Embedding to Improve Predictive Models for Companies, text, June 2022; (https://digital.library.unt.edu/ark:/67531/metadc2047084/: accessed April 20, 2024), University of North Texas Libraries, UNT Digital Library, https://digital.library.unt.edu; crediting UNT College of Information.

Back to Top of Screen