Abstract
Stock market prediction is a challenging task due to the nonlinear, dynamic, and highly volatile nature of financial time-series data. To address these challenges and enhance prediction accuracy, this study proposes a deep learning–based stock market prediction system integrating Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM) networks, and Artificial Neural Networks (ANN). The LSTM model is employed to capture long-term temporal dependencies in historical stock price data, while CNN is utilized to automatically extract meaningful local patterns and trends from time-series representations. In addition, ANN is used to model complex nonlinear relationships between stock prices, trading volumes, market sentiment, and macroeconomic indicators.