To improve the accuracy and resilience of stock price predictions, this study investigates the synergistic integration of modern forecasting approaches, including the Kalman filter, XG Boost algorithm, and linear regression. Understanding the inherent difficulties in simulating the dynamic and erratic nature of financial markets, the goal of this research is to provide a comprehensive framework that makes use of the advantages of each algorithmic technique. Known for its efficiency when processing time-series data, the Kalman filter is used to dynamically modify its forecasts in response to real-time data, allowing it to capture and adjust to changing market conditions. This is enhanced by the ability of the XGBoost algorithm, a potent machine learning method, to identify intricate patterns and nonlinear correlations in the financial data. In addition, the interpretability and simplicity of linear regression are used to provide a baseline model for comparison. Our research shows the combined effectiveness of these approaches in reducing the inherent uncertainties of financial markets through a thorough analysis of past stock data. Combining the Kalman filter, XGBoost, and linear regression improves the model’s ability to adjust to a variety of market conditions while also improving prediction accuracy. The empirical findings highlight the possibility of developing a stock price prediction model that is more trustworthy, opening the door to better financial market decision-making. This study offers a sophisticated solution to the problems associated with stock price forecasting, which adds significant insights to the field’s growing state.