A simple, effective distance and density based outlier detection algorithm

Outliers are eccentric data points with anomalous nature. Clustering outliers has received a lot of attention in the processing community. But, they inordinately affect quality results obtained case popular clustering algorithms during process finding an optimal solution. In this work, we propose novel method to classify grouping characteristics as either outlier or not. We use both distance and density particular point respect rest for process. Distances used find at extremities while densities identify sparsest spaces. Further, every model take into account aspect generalization order work robustly even out box situations. Hence, our approach provides model. The accuracy proposed is measured using area under curve (AUC) was found highest cardioto set -AUC value-0.90 second AUC value Spambase -0.52 several other datasets demonstrate usage proposed.