In the rapidly evolving world of e-commerce, predicting mobile phone booking cancellations is vital for optimizing customer satisfaction and operational efficiency. This study explores the use of machine learning algorithms, specifically Support Vector Machines (SVM) and Logistic Regression (LR), to forecast booking cancellations on various e-commerce platforms. Historical data comprising customer demographics, booking details, and transactional behaviors are analyzed to identify factors influencing cancellations. The models are trained and examined using metrics like precision, accuracy, recall, and F1-score to confirm robust performance. Results demonstrate that both SVM and LR can effectively predict cancellations, with SVM showing slightly better performance in terms of precision. The findings indicate that leveraging predictive analytics can assist e-commerce platforms in preemptively managing resources, reducing cancellation rates, and improving overall customer retention. Future research could explore integrating more advanced algorithms and additional features for enhanced accuracy.