Outlier Detection Using Unsupervised and Semi-Supervised Technique on High Dimensional Data

Outlier detection is useful for credit card fraud detection. Due to drastic increase in digital frauds, there is a lot of financial losses and therefore various techniques are developed for fraud detection and applied to diverse business fields. In high-dimensional data, outlier detection presents some challenges because of increment of dimensionality. In this paper, the proposed model aims to implement unsupervised outlier detection technique using KNN, AntiHub and AntiHub2 algorithm and semi-supervised outlier detection technique in which first extracting negative instances by KNN and then with fuzzy clustering of both positive and negative example with distributed approach to find credit card fraud. Hence this method will provide more accurate results as compared to other methods.