EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A comparative study on effect of news sentiment on stock price prediction with deep learning architecture

Keshab Raj Dahal, Nawa Raj Pokhrel, Santosh Gaire iD, Sharad Mahatara, Rajendra P Joshi, Ankrit Gupta, Huta R Banjade, Jeorge Joshi

PLOS ONE · 25.04.2023 · 18 (4) · e0284695

DOI: 10.1371/journal.pone.0284695 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS ONE, online erschienen am 25.04.2023. Verfasst von Keshab Raj Dahal und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Statistics, Truman State University, Kirksville, MO, United States of America. Hauptthemen laut MEDLINE: Artificial Intelligence, Deep Learning. Die Arbeit wurde bisher 39-mal zitiert (Crossref) und nennt 71 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The accelerated progress in artificial intelligence encourages sophisticated deep learning methods in predicting stock prices. In the meantime, easy accessibility of the stock market in the palm of one’s hand has made its behavior more fuzzy, volatile, and complex than ever. The world is looking at an accurate and reliable model that uses text and numerical data which better represents the market’s highly volatile and non-linear behavior in a broader spectrum. A research gap exists in accurately predicting a target stock’s closing price utilizing the combined numerical and text data. This study uses long short-term memory (LSTM) and gated recurrent unit (GRU) to predict the stock price using stock features alone and incorporating financial news data in conjunction with stock features. The comparative study carried out under identical conditions dispassionately evaluates the importance of incorporating financial news in stock price prediction. Our experiment concludes that incorporating financial news data produces better prediction accuracy than using the stock fundamental features alone. The performances of the model architecture are compared using the standard assessment metrics —Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE), and Correlation Coefficient (R). Furthermore, statistical tests are conducted to further verify the models’ robustness and reliability.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Artificial IntelligenceDeep LearningReproducibility of ResultsAttitude

Autor:innen und Institutionen

  • Department of Statistics, Truman State University, Kirksville, MO, United States of America.
  • Department of Physics and Computer Science, Xavier University of Louisiana, New Orleans, LA, United States of America.
  • Department of Physics, The Catholic University of America, Washington, DC, United States of America.
  • Department of Physics, New Mexico State University, Las Cruces, NM, United States of America.
  • TQuT Inc., Rockford, MI, United States of America.
  • Department of Computer Science, Central Michigan University, Mount Pleasant, MI, United States of America.

ORCID-Profile: Santosh Gaire

Zitieren

APA

Dahal, K. R., Pokhrel, N. R., Gaire, S., Mahatara, S., Joshi, R. P., Gupta, A., Banjade, H. R., & Joshi, J. (2023). A comparative study on effect of news sentiment on stock price prediction with deep learning architecture. PLOS ONE, 18(4), e0284695. https://doi.org/10.1371/journal.pone.0284695

Vancouver

Dahal KR, Pokhrel NR, Gaire S, Mahatara S, Joshi RP, Gupta A, et al. A comparative study on effect of news sentiment on stock price prediction with deep learning architecture. PLOS ONE. 2023;18(4):e0284695. doi:10.1371/journal.pone.0284695

BibTeX
@article{Dahal2023,
  author = {Dahal, Keshab Raj and Pokhrel, Nawa Raj and Gaire, Santosh and Mahatara, Sharad and Joshi, Rajendra P and Gupta, Ankrit and Banjade, Huta R and Joshi, Jeorge},
  title = {A comparative study on effect of news sentiment on stock price prediction with deep learning architecture},
  journal = {PLOS ONE},
  year = {2023},
  volume = {18},
  number = {4},
  pages = {e0284695},
  doi = {10.1371/journal.pone.0284695}
}
Kostenlos starten →