Effective anomaly detection techniques are now essential to ensure the security and integrity of computer networks due to the complexity and volume of network traffic data. Traditional techniques often struggle to cope with evolving new attacks and fail to detect novel anomalies. This has led to the adoption of machine learning algorithms, which can automatically learn patterns and identify deviations from normal network behaviors. In this paper, we represent a novel approach to detect anomalies in the network using machine learning models like Decision Tree and Random Forest Classifier. Our approach consists of a system for detecting anomalies in real-time data and generating an email notification whenever anomalies are detected. The email includes the details of the network traffic data that have been identified as anomalies. The proposed methodology is implemented using the KDD CUP dataset. Furthermore, the machine learning models are deployed and evaluated using machine learning techniques.