Improving Portfolio Performance via Natural Language Processing Methods

Di Jia Su; John M. Mulvey; H. Vincent Poor

doi:10.3905/jfds.2022.1.088

Improving Portfolio Performance via Natural Language Processing Methods

Di Jia Su, John M. Mulvey, H. Vincent Poor

Research output: Contribution to journal › Article › peer-review

1 Scopus citations

Abstract

Recent natural language processing (NLP) breakthroughs have proven effective for addressing many language-directed tasks, such as completing sentences and addressing search queries. This technology has been successfully implemented by tech firms including Google and others. An important element consists of language embeddings linked to pretraining systems. This ar ticle describes NLP concepts and their application to por tfolio models via a modern version of sentiment analysis. The authors demonstrate the advantages of employing information from Twitter along with the NLP for constructing a portfolio of stocks, especially during unusual events such as the COVID-19 pandemic.

Original language	English (US)
Pages (from-to)	37-49
Number of pages	13
Journal	Journal of Financial Data Science
Volume	4
Issue number	2
DOIs	https://doi.org/10.3905/jfds.2022.1.088
State	Published - Mar 1 2022
Externally published	Yes

All Science Journal Classification (ASJC) codes

Information Systems and Management
Artificial Intelligence
Information Systems
Business, Management and Accounting (miscellaneous)
Business and International Management
Finance
Computational Theory and Mathematics
Strategy and Management

Access to Document

10.3905/jfds.2022.1.088

Cite this

@article{b84ac9573f0b421b89dcb28e547af2b1,

title = "Improving Portfolio Performance via Natural Language Processing Methods",

abstract = "Recent natural language processing (NLP) breakthroughs have proven effective for addressing many language-directed tasks, such as completing sentences and addressing search queries. This technology has been successfully implemented by tech firms including Google and others. An important element consists of language embeddings linked to pretraining systems. This ar ticle describes NLP concepts and their application to por tfolio models via a modern version of sentiment analysis. The authors demonstrate the advantages of employing information from Twitter along with the NLP for constructing a portfolio of stocks, especially during unusual events such as the COVID-19 pandemic.",

author = "Su, {Di Jia} and Mulvey, {John M.} and Poor, {H. Vincent}",

note = "Publisher Copyright: {\textcopyright} 2022 With Intelligence Ltd.",

year = "2022",

month = mar,

day = "1",

doi = "10.3905/jfds.2022.1.088",

language = "English (US)",

volume = "4",

pages = "37--49",

journal = "Journal of Financial Data Science",

issn = "2640-3943",

publisher = "With intelligence",

number = "2",

}

TY - JOUR

T1 - Improving Portfolio Performance via Natural Language Processing Methods

AU - Su, Di Jia

AU - Mulvey, John M.

AU - Poor, H. Vincent

PY - 2022/3/1

Y1 - 2022/3/1

N2 - Recent natural language processing (NLP) breakthroughs have proven effective for addressing many language-directed tasks, such as completing sentences and addressing search queries. This technology has been successfully implemented by tech firms including Google and others. An important element consists of language embeddings linked to pretraining systems. This ar ticle describes NLP concepts and their application to por tfolio models via a modern version of sentiment analysis. The authors demonstrate the advantages of employing information from Twitter along with the NLP for constructing a portfolio of stocks, especially during unusual events such as the COVID-19 pandemic.

AB - Recent natural language processing (NLP) breakthroughs have proven effective for addressing many language-directed tasks, such as completing sentences and addressing search queries. This technology has been successfully implemented by tech firms including Google and others. An important element consists of language embeddings linked to pretraining systems. This ar ticle describes NLP concepts and their application to por tfolio models via a modern version of sentiment analysis. The authors demonstrate the advantages of employing information from Twitter along with the NLP for constructing a portfolio of stocks, especially during unusual events such as the COVID-19 pandemic.

UR - http://www.scopus.com/inward/record.url?scp=85132640757&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85132640757&partnerID=8YFLogxK

U2 - 10.3905/jfds.2022.1.088

DO - 10.3905/jfds.2022.1.088

M3 - Article

AN - SCOPUS:85132640757

SN - 2640-3943

VL - 4

SP - 37

EP - 49

JO - Journal of Financial Data Science

JF - Journal of Financial Data Science

IS - 2

ER -

Improving Portfolio Performance via Natural Language Processing Methods

Abstract

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this