Preprint Article Version 1 This version is not peer-reviewed

GRUvader ‐ Sentiment Informed Stock Market Prediction

Version 1 : Received: 29 October 2024 / Approved: 30 October 2024 / Online: 31 October 2024 (09:22:33 CET)

How to cite: Mamillapalli, A.; Ogunleye, B.; Timoteo Inacio, S.; Shobayo, O. GRUvader ‐ Sentiment Informed Stock Market Prediction. Preprints 2024, 2024102465. https://doi.org/10.20944/preprints202410.2465.v1 Mamillapalli, A.; Ogunleye, B.; Timoteo Inacio, S.; Shobayo, O. GRUvader ‐ Sentiment Informed Stock Market Prediction. Preprints 2024, 2024102465. https://doi.org/10.20944/preprints202410.2465.v1

Abstract

Stock price prediction is challenging due to global economic instability, high volatility and complexity of financial markets. Hence, this study compared several machine learning algorithms for stock market prediction and further examine the influence of sentiment analysis indicator in predicting stock price. Our results are in two-fold. Firstly, we present a lexicon-based sentiment analysis approach for identifying sentiment features and thus, evidence the correlation between the sentiment indicator and stock price movement. Secondly, we propose the use of GRUVader, an optimal gated recurrent unit networks for stock market prediction. Our findings suggest stand-alone models struggle when compared with AI-enhanced models. Thus, our paper made further recommendations on latter systems.

Keywords

ARIMA; GRU; machine learning; sentiment analysis; time series analysis

Subject

Computer Science and Mathematics, Artificial Intelligence and Machine Learning

Comments (0)

We encourage comments and feedback from a broad range of readers. See criteria for comments and our Diversity statement.

Leave a public comment
Send a private comment to the author(s)
* All users must log in before leaving a comment
Views 0
Downloads 0
Comments 0


×
Alerts
Notify me about updates to this article or when a peer-reviewed version is published.
We use cookies on our website to ensure you get the best experience.
Read more about our cookies here.