GRUvader: Sentiment-Informed Stock Market Prediction

TL;DR

This paper introduces GRUvader, a gated recurrent unit network that incorporates sentiment analysis to improve stock market prediction accuracy, demonstrating the importance of sentiment features in financial forecasting.

Contribution

The study presents a novel GRUvader model that integrates sentiment analysis with advanced neural networks for enhanced stock prediction performance.

Findings

Sentiment features correlate with stock price movements.

GRUvader outperforms stand-alone models in prediction accuracy.

Sentiment-informed models are more effective than traditional methods.

Abstract

Stock price prediction is challenging due to global economic instability, high volatility, and the complexity of financial markets. Hence, this study compared several machine learning algorithms for stock market prediction and further examined the influence of a sentiment analysis indicator on the prediction of stock prices. Our results were two-fold. Firstly, we used a lexicon-based sentiment analysis approach to identify sentiment features, thus evidencing the correlation between the sentiment indicator and stock price movement. Secondly, we proposed the use of GRUvader, an optimal gated recurrent unit network, for stock market prediction. Our findings suggest that stand-alone models struggled compared with AI-enhanced models. Thus, our paper makes further recommendations on latter systems.