The enormous potential for medical, military and defence, environmental, industrial, infrastructure protection, and commercial applications of wireless sensor networks has drawn a lot of attention in research and development. These applications include the ability for the sensors to interact with one another under remote control. Wide-ranging uses for a Wireless Sensor Network (WSN) include tracking communication targets and environmental monitoring. The wireless ports on the sensor nodes allow for communication between the nodes and another network. Security is a major issue in wireless sensor networks due to numerous limitations. The sensor nodes are open targets for numerous attacks when left unattended in a communication context. The dataset is analysed using the supervised machine learning technique (SMLT), which may capture a variety of data, including variable detection, univariate analysis, bivariate analysis, and multivariate analysis, as well as treatments for missing values. In order to discover which machine learning algorithm is the most effective at foretelling the types of WSN attacks, comparative studies of the algorithms have been conducted. The outcomes demonstrate that the suggested machine learning algorithm technique's efficacy may be compared to the highest levels of accuracy, precision, recall, F1 Score, sensitivity, and specificity.