This study presents a hybrid machine learning model that enhances indoor localization accuracy by combining Neural Networks, Decision Trees, Support Vector Regression, and Gradient Boosting Regressor. Accurate indoor positioning is a critical challenge due to the unreliability of Global Positioning System signals in enclosed spaces. Wireless Fidelity based positioning has emerged as a practical alternative, leveraging existing access points to estimate locations without additional infrastructure. Two main use cases for such an application are guiding guests through a building and tracking the movement of individuals, such as student attendance in a university or employees in a company. The model's performance is evaluated using key metrics such Mean Absolute Error, Mean Squared Error, Root Mean Squared Error, and R² score, along with classification-based evaluation and learning curve analysis to assess generalization and training efficiency. Experimental results show that the hybrid approach outperforms individual models by leveraging their strengths, leading to improved positioning precision. These findings demonstrate the potential of machine learning-driven indoor localization and pave the way for more accurate and efficient positioning technologies.