With the goal to predict the likelihood, CTR that is click through rate is a task that is critical in digital advertising. Use of XGBoost as a powerful machine learning model for forecasting CTR in an advertising system is being explored by this paper. XGBoost is chosen due to the high dimensional nature of the data set containing both categorical and numerical features and because of its scalability and efficiency in handling large data set. It also provides robust performance in managing overfitting. Key performance metrics such as accuracy, Precision and recall have been evaluated in the study for the purpose of comparing the performance of XGBoost with other machine learning models. Along with particular focus on XGBoost’s predictive accuracy, we highlight the strengths and weaknesses of each model in this comparison. We offer the marketers a reliable data driven tool which will optimize their advertisement campaign by contributing to the ongoing advancements in CTR Prediction models. This ultimately helps to select the best model which enhances advertising efficiency and hence improves the overall outcome of the campaign.