Vol. 7, Issue 1, Part F (2025)

Stock market prediction remains a complex challenge due to its volatile and dynamic nature. This study leverages deep learning techniques, specifically Long Short-Term Memory (LSTM) networks, to forecast stock prices using historical market data. By utilizing 20 years of Google's stock data from Yahoo Finance, the research explores how LSTM can capture intricate patterns and temporal dependencies in financial time series. The study involves data pre-processing, exploratory data analysis, and LSTM model implementation to predict future stock prices. Results indicate that deep learning significantly improves prediction accuracy compared to traditional statistical models. This research highlights the potential of LSTM in stock market forecasting and suggests avenues for further improvement, such as incorporating external market indicators and sentiment analysis.