In the dynamic landscape of the Google Play Store, predicting app ratings remains a critical yet challenging endeavour. This study focuses on advancing the accuracy of rating predictions through the application of machine learning algorithms, specifically Support Vector Machines (SVM), and Gradient Boosting. These algorithms are chosen for their unique capabilities in capturing diverse patterns within the vast array of app data. Addressing contemporary challenges, the research confronts issues such as the proliferation of diverse applications, evolving user preferences, and the influence of biased reviews. SVM, known for its effectiveness in high-dimensional spaces, tackles the challenge of diverse data types and complex relationships, while Gradient Boosting enhances predictive accuracy through sequential model ensembles. Emphasizing the need for adaptability in the face of emerging issues like fake reviews and rapidly shifting user sentiments, this research aims to contribute nuanced insights into the rating prediction landscape. By leveraging a diverse set of machine learning algorithms, the study aspires to provide a comprehensive and robust framework for enhancing our understanding of app ratings on the Google Play Store, addressing the latest challenges in this dynamic ecosystem.