The inception of a system that can detect if there is an intrusion into the host system is conceptualized. This is performed using standard machine-learning algorithms. Our focus is to collect information about the network traffic and related domains of the host system and store it in a dataset. The dataset is then used to critically examine the data and find a pattern for the normal systems. These data are then comparatively studied by the algorithms to detect if there is a greater probabilistic chance of having an anomaly in the system. We are using a binary classification model that predicts the possibility of malicious activities on the host server through the collected dataset. In this work, we have integrated a user-interactive web page that takes certain inputs from the user, which are necessary for accurate results. Random forest outperforms all four machine learning algorithms (k nearest neighbor, logistic regression, decision tree, and random forest) on the same dataset, with an accuracy of 99.6%. Hence, for our web page development, we use a random forest algorithm that shows the output according to the inputs given by the users.