Over-the-top (OTT) apps, which give users access to a variety of multimedia content, have seen a sharp increase in appeal in recent years. Therefore, it has become crucial for platform suppliers and advertising to comprehend customer behavior. This research suggests the development of a user consumption categorization system based on machine learning (ML) such as Decision Tree (DT), Random Forest (RF), Regression Algorithm, k-Nearest Neighbour (KNN), Bayesian Algorithm (BA), Gradient Boosting (GB), and XGBoost Classifier in order to categorize users based on their consumption rate, which may be classified as low, medium, or high. The study will use data preprocessing methods to customize the data and prepare it for clustering. The next step is to compare the accuracy of various ML models to determine which one best predicts the user’s usage rate. We will explore the boundaries of each algorithm and merge the system with data mining and analytics tools. This study will progress the field of machine learning by providing a practical application for categorizing user consumption patterns and may be helpful to OTT platform providers, marketers, and data analytics specialists.