The task of identifying unwanted or legitimate network traffic is to be performed by a supervised machine learning system. A mix of choosing features technique and supervised learning algorithm has been utilized to determine the optimal model taking detection effectiveness into account. This study shows that when it comes to network traffic classification, Artificial Neural Network (ANN) dependent machine learning enhanced wrapper choice of features performs better than Support Vector Machine (SVM) method. ANN and SVM supervised machine learning algorithms are employed to categorize network traffic employing the NSL-KDD dataset in order to assess performance. IDS has recently been deployed as an additional line of protection to effectively safeguard the networks. An intrusion detection system (IDS) is an application or equipment that keeps an eye on and evaluates data flow via the network in order to spot unusual or invasive data in the system. A comparison of approaches reveals that, in terms of intrusion detection effectiveness rate, the suggested model is more effective than other models already in use. Particularly now that technology is so important, we must advance with an upgrading mentality.