Grid-ODF: Detecting Outliers Effectively and Efficiently in Large Multi-dimensional Databases

Outlier detection is an important task in data mining that enjoys a wide range of applications such as detections of credit card fraud, criminal activity and exceptional patterns in databases. In recent years, there have been numerous research work in outlier detection and the new notions such as distance-based outliers and density-based local outliers have been proposed. However, the existing outlier detection algorithms suffer the drawbacks that they are inefficient in dealing with large multi-dimensional datasets and most of them are only able to capture certain kinds of outliers. In this paper, we will propose a novel outlier mining algorithm, called Grid-ODF, that takes into account both the local and global perspectives of outliers for effective detection. The notion of Outlying Degree Factor (ODF), that reflects the factors of both the density and distance, is introduced to rank outliers. A grid structure partitioning the data space is employed to enable Grid-ODF to be implemented efficiently. Experimental results show that Grid-ODF outperforms existing outlier detection algorithms such as LOF and KNN-distance in terms of effectiveness and efficiency.