A hybrid outlier detection algorithm based on partitioning clustering and density measures

Abstract

Outlier detection is an important issue in the realm of data mining. Several applications relay on outlier detection such as intrusion detection, fraud detection, medical and public health data, image processing, etc. Clustering-based outlier detection algorithms are considered as the most important outlier detection approaches. They provide high detection rate, however, they suffer from high false positives. In this paper, we propose a clustering-based outlier detection algorithm that supports searching for outliers not only in small clusters but also in large clusters with an optimized calculation methodology. The experimental results demonstrate the good performance of the algorithm in terms of detection accuracy by increasing the detection rate, decreasing the false positives, and minimizing outlierness factor calculations.