A STOCK PRICE PREDICTION MODEL BASED ON INVESTOR SENTIMENT AND OPTIMIZED DEEP LEARNING

Abstract

Stock price prediction has become a significant research area in financial analytics due to its potential to assist investors in making informed investment decisions. Traditional prediction methods primarily rely on historical market data and technical indicators; however, they often fail to capture the influence of investor emotions and market sentiment on stock price movements. This paper proposes a stock price prediction model based on investor sentiment and optimized deep learning techniques. The proposed framework integrates sentiment information extracted from financial news, social media platforms, and investor discussions with historical stock market data to enhance prediction accuracy. Advanced deep learning architectures are employed to learn complex nonlinear relationships between market indicators and investor behavior. Furthermore, optimization techniques are incorporated to improve model convergence, reduce prediction errors, and enhance overall forecasting performance. By combining sentiment analysis with optimized deep learning models, the proposed approach provides a comprehensive understanding of market dynamics and enables more accurate stock price forecasting. Experimental analysis demonstrates that the integration of investor sentiment significantly improves prediction reliability and supports better investment decision-making in dynamic financial markets.