Comparing Decision Tree And Gradient Boosting Algorithms In Predicting Stock Market Trends

Abstract

This study presents a comparative analysis of Decision Tree and Gradient Boosting algorithms in predicting stock market trends. Utilizing a comprehensive dataset of historical stock prices and technical indicators, the performance of both models was evaluated across key metrics, including accuracy, precision, recall, F1-score, and ROC-AUC. The findings reveal that the Gradient Boosting algorithm significantly outperforms the Decision Tree in all aspects, achieving higher accuracy, better precision, and greater overall model robustness. The results highlight the superior capability of Gradient Boosting in capturing complex, non-linear patterns in financial data, making it a more reliable tool for stock market prediction. This research underscores the importance of advanced machine learning techniques in financial forecasting and provides valuable insights for practitioners in the field.