This article explores the application of advanced machine learning techniques in financial forecasting, focusing on the prediction of stock market trends. Leveraging historical data from the S&P 500 index, the study investigates the efficacy of Long Short-Term Memory (LSTM) and Bidirectional LSTM (BiLSTM) networks, as well as traditional linear regression models, in capturing complex market dynamics and improving predictive accuracy. Through meticulous data pre-processing, model training, and evaluation, the research demonstrates the superiority of deep learning approaches over conventional regression methods, highlighting their potential to revolutionize financial decision-making processes. Findings reveal that LSTM and BiLSTM networks outperform linear regression models, providing stakeholders with powerful predictive tools to enhance investment strategies and mitigate risks. The study also explores model integration techniques to combine the strengths of multiple models, further enhancing predictive performance.