Hyper Graph Deviation Comparison & Cluster Relation In Categorical Data

Abstract

Outlier detection is one of the most important issues in recent years. Outlier detection is the process of detecting errors in data. The recent methods are mostly based on Numerical data, but these methods are not suitable for real time data such as web pages, business transactions etc., which are known as Categorical data. It is difficult to find outliers in categorical data. In this paper, we propose an approach to find outliers those are Comparison of Deviations. In Comparison of deviation method, we use hyper graph to calculate the deviations of each object in the database, and we measure the similarity between attributes in database.