TAF PUBLISHING

In this study, the web traffic was analyzed via machine learning (ML) support, and incoming traffic was visualized after real-time classification, prioritizing stability and performance, which are indispensable for real-time applications. Websocket technology was used for instantaneous and fast data transfer. Processes may be blocked due to asynchronous operating structure when Hyper-Text Transfer Protocol (HTTP) traffic is intensive. Synchronous operation of the system was causing both delays and negatively affecting the efficiency of the application. To overcome this bottleneck, the developed application used asynchronous libraries instead of synchronous ones. The essential features of the study were the analysis of HTTP packets captured in real-time, classifying the packets according to whether they are safe or suspicious using ML algorithms, and real-time display of the acquired results. In this way, incoming traffic was classified smartly without getting lost in thousands of log files. A success rate of 96.49% was attained using the logistic regression model, which is very successful in classification.