The stock market presents a dynamic and challenging environment where investors seek opportunities while managing uncertainties. Accurately predicting stock price movements is crucial for informed decision-making and maximizing returns. In our research, we explore the application of Long Short-Term Memory (LSTM) networks, a type of recurrent neural network recognized for its ability to learn from sequential data, in predicting stock market movements. We utilize a comprehensive dataset encompassing Nifty 100 intraday and daily price data from 2015 to 2022. Our methodology involves thorough data preprocessing, LSTM model development, rigorous training, testing procedures, and detailed evaluation. The primary objective of our study is to assess the effectiveness of LSTM networks in forecasting stock prices and to explore their potential to enhance financial forecasting practices. We apply our methodology to prominent companies such as Apple, BPCL, Tata Steel, and TCS, illustrating how LSTM networks can potentially optimize investment strategies and decision-making processes in the dynamic stock market landscape. This research underscores the promising role of advanced machine learning techniques in providing valuable insights for investors and adapting to the complexities of stock market dynamics.