Publicly traded corporations can generate funds by selling ownership shares, also known as stocks, to investors through the stock market. Various factors such as the company's financial performance, market trends, geopolitical events, and economic conditions influence the demand and supply of a stock and thereby determine its value. The study aims to compare multiple machine learning models to determine the most effective approach to forecast stock closing prices. The study employs Long Short Term Memory (LSTM), Bidirectional Long Short Term Memory (Bi-LSTM), Stacked Long Short Term Memory (stacked LSTM), and Genetic Algorithm optimized Recurrent Neural Networks to generate predictions. By studying the prediction accuracy and performance of different machine learning algorithms, the research aims to identify the best approach for predicting stock prices. To achieve this, the researchers conducted independent investigations into each method, resulting in a comprehensive understanding of these machine learning algorithms.