This paper focuses on enhancing the performance of intrusion detection systems (IDS) using machine learning models on the UNSW-NB15 dataset. The study employs logistic regression, support vector machine (SVM), decision tree, and random forest algorithms, utilizing exploratory data analysis and feature selection techniques. The Random Forest model is identified as the most effective, achieving a high F1 score of 97.80%, accuracy of 98.63%, and a low false alarm rate of 1.36%. The research highlights the importance of data analytics and machine learning in improving IDS accuracy and reducing false positives, making it a valuable contribution to cybersecurity. The study also discusses the methodology, dataset description, and results, emphasizing the significance of hyperparameter tuning and feature selection in enhancing model performance. The findings suggest that the Random Forest model is a robust solution for enhancing IDS security, with potential applications in real-world network environments.This paper focuses on enhancing the performance of intrusion detection systems (IDS) using machine learning models on the UNSW-NB15 dataset. The study employs logistic regression, support vector machine (SVM), decision tree, and random forest algorithms, utilizing exploratory data analysis and feature selection techniques. The Random Forest model is identified as the most effective, achieving a high F1 score of 97.80%, accuracy of 98.63%, and a low false alarm rate of 1.36%. The research highlights the importance of data analytics and machine learning in improving IDS accuracy and reducing false positives, making it a valuable contribution to cybersecurity. The study also discusses the methodology, dataset description, and results, emphasizing the significance of hyperparameter tuning and feature selection in enhancing model performance. The findings suggest that the Random Forest model is a robust solution for enhancing IDS security, with potential applications in real-world network environments.