Our proposal centers on the development of a robust tool designed to forecast stock prices by leveraging a sophisticated combination of advanced techniques. We're merging spatial features, which essentially encapsulate the distinctive attributes of individual stocks, with the powerful capabilities of long-and-short-term memory networks (LSTM). These networks excel at recognizing and interpreting patterns and trends over extended periods. By integrating these two elements, our model gains the ability to capture both short-lived fluctuations and enduring trends within stock prices.This fusion of spatial features and LSTM networks represents a significant advancement in stock price prediction methodologies. We're confident that this innovative approach will surpass existing methods in terms of accuracy and reliability. To validate our confidence, we're conducting rigorous testing and refinement of the system using diverse sets of data. This ensures that our model performs effectively across various market conditions and scenarios, thereby instilling trust among investors seeking dependable insights into stock market trends. Key Word: Long and Short-Term Memory, Time-Series Data, Yahoo Finance.