Modern cyber security relies heavily on intrusion detection in network traffic to quickly identify and mitigate security threats. Conventional intrusion detection systems frequently depend on lone, stand- alone models that could find it difficult to change with the ways that network attacks are evolving. In order to overcome this difficulty, we provide an ensemble-based strategy that improves threat detection effectiveness and accuracy by utilizing the strength of several intrusion detection models. Increasing security measures against data breaches and network invasions is essential due to the ever-growing usage of the Internet and networks. As intrusions are frequently hidden within of valid network packets, firewalls have a difficult time identifying and stopping them. Furthermore, the majority of network monitoring systems and algorithms find it increasingly difficult to handle the sheer volume of network traffic. Various intrusion detection strategies have been proposed in response to these issues, with machine learning techniques emerging as a possible route for handling these situations. In this paper, an intrusion detection system (IDS) that makes use of stacking ensemble learning is presented. The three fundamental machine learning models that make up the core ensemble are k-nearest-neighbours, Decision Tree, and Random Forest. In order to improve classification performance, the suggested system combines a total of seven machine learning algorithms with pre-processing methods. By merging the outputs of the underlying models with a meta-model embodied by the Logistic Regression algorithm, the stacking ensemble technique improves performance. The UNSW-NB15 dataset is used to assess the efficacy of the IDS. The suggested IDS obtains an astounding 96.16% accuracy rate in the training phase and an even greater 97.95% accuracy rate in the testing phase. Impressive precision scores as well—97.78% during training and 98.40% during testing—are obtained. The system's capacity to identify and reduce network intrusions is demonstrated by these results, which show notable enhancements across a range of measuring criteria