Adaptive Parallel Algorithm for Outlier Detection Using Ranking Strategy

Outlier Detection is very much popular in Data Mining field and it is an active research area due to its various applications like fraud detection, network sensor, email spam, stock market analysis, and intrusion detection and also in data cleaning. Most widely use of outlier detection in medical diagnostics to detect irregular patterns in patient medical records which could be symptoms of a new disease So, it is very important to detect outlier in large data set very efficiently, here we have discussed various methods for outlier detection like a very simple and easy method is distance-based outlier detection in this method outlier can be detected based on its distance to predefined points in a given data set, find out the nearest neighbor and based on it detect points as outliers, but it is very challenging task to develop such method which is efficiently detect outliers and also can be applicable to large data set effectively. Ranking based outlier detection is the new area in the outlier detection, various ranking strategies apply to detect outliers but no one is much power full which we can apply for large dimensional datasets. So In this paper we have made a survey to implement An Adaptive algorithm using ranking strategies for large dimensional datasets and also to overcome the limitation of existing system.