Abstract
The stock market serves as a crucial venue for the exchange of shares of publicly traded companies, and it serves as an indicator of a country's economic well-being. Despite inherent dangers, it also presents the possibility of long-term financial gains. In recent years, Long Short-Term Memory (LSTM) networks have been crucial in financial market analysis for predicting stock prices. This paper introduces a sophisticated LSTM model that has been enhanced using the Attributed Single-Objective Comprehensive Learning Particle Swarm Optimization (A-SOCLPSO) technique to improve the accuracy of stock price prediction. The model's design is optimized to enhance predicted accuracy by utilizing five years of historical data from 20 businesses listed in the DJIA, with a 60-day look-back period. The proposed model LSTM-A-SOCLPSO outperformed existing state-of-the-art models, making it a valuable alternative for stock price prediction. This study highlights the efficacy of combining LSTM networks with sophisticated optimization techniques to enhance predictions of financial market trends.
DOI:10.61416/ceai.v27i4.9583