Analyzing Machine Learning Frameworks for Anomaly Detection on Web Server Log Data

The field of anomaly detection has been around for decades and is still one of the most active areas of research in many fields. To build an efficient anomaly identification system, scholars and innovators must first understand the intricate configuration of data that exhibits noise, explore energetic anomaly trends, and monitor anomalies with restricted labels. Several preliminary works on anomaly detection have been developed with the advent of machine learning. This study conducts detailed explorations of deep learning (DL) and machine learning (ML) frameworks for anomaly sensing on web server logs. The trials comparative results will help identify suitable ML frameworks and algorithms for researchers and industrial users in anomaly detection.