<![CDATA[Forecasting price patterns in the stock market poses a complicated and intricate task due to numerous uncertain factors and variables that influence market value. This study conducts a comparative evaluation of three popular computational learning approaches, namely Random Forest, K-Nearest Neighbors (KNN), and XGBoost, for predicting stock price changes. The research findings indicate that Random Forest achieves higher ROC scores, while XGBoost exhibits superior performance in relation to accuracy, recall, and precision. The Windowing method is also applied to the dataset to address overfitting issues. This study offers valuable knowledge for professionals and researchers in the domain of stock price prediction, enabling them to choose the optimal model based on preferred evaluation metrics.]]>
Copyrights © 2023
