Isolation Forest Based Anomaly Detection: A Systematic Literature Review
Wahid Salman Al Farizi, Indriana Hidayah, Muhammad Nur Rizal
Abstract
Anomaly detection using machine learning algorithms is rising lately, especially with increased data volume and velocity. One of the most recent anomaly detection algorithms is Isolation Forest (IF). Despite its simplicity, it excels at dealing with high-dimensional data and excels at speed. However, IF is not without weaknesses, and several researchers have found its weaknesses and at the same time provide solutions. Therefore, to help understanding researches related to IF, this paper will discuss 17 studies related to IF improvement by conducting a systematic literature review that comprehensively discusses IF weaknesses, types of data, and causes of occurrence, as well as dissecting the solutions offered and the fields of research that use IF. From the review, it is known that the main cause of the weakness of IF is the random selections of variables in the data split and the solutions proposed by the researchers are divided into three types: pre-IF, post-IF and method improvement. To our knowledge, there is no literature review related to IF improvement, and we expect this paper to help other researchers in developing anomaly detection based on IF.