Stock market prediction has long been a challenging task due to its complex and dynamic nature. Investors, traders, and financial analysts seek accurate methods to forecast stock prices and make informed decisions. In recent years, machine learning techniques, particularly decision tree-based methods, have gained prominence for their ability to handle complex data and provide interpretable results. This research paper aims to explore the application of decision tree-based methods, including traditional decision trees, random forests, and gradient boosting, in stock market prediction. We analyze historical stock price data and various relevant features to construct predictive models and evaluate their performance. The study also investigates the impact of different parameters and feature engineering techniques on model accuracy and robustness. Our findings demonstrate the potential of decision tree-based methods as effective tools for stock market prediction and highlight their advantages and limitations in this domain..