Cybercrime is one of the fastest-growing crimes worldwide. It is observed that every seven seconds, cyber attackers penetrate cyber systems. While detecting an anomaly or attack, the log system is one of the crucial components of any system storing and managing all the events. It has always been challenging to detect an anomaly in logs. This is because of continuous and ever-changing log events and their mutability property. In this paper, we develop a machine learning-based artificial intelligence approach to address this issue of log analysis by proposing two modules. The first one is anomaly detection using different machine learning models. The second one is a distributed immutable storage system for securely storing the logs. In addition, we present a descriptive and user-friendly web application by integrating all modules using HTML, CSS, and Flask Framework on the Heroku cloud environment. The results demonstrate that the proposed hybrid machine learning models are capable of achieving 99.7% accuracy in detecting network anomalies.