Outlier detection for high dimensional data

The outlier detection problem has important applications in the eld of fraud detection, network robustness analysis, and intrusion detection. Most such applications are high dimensional domains in which the data can contain hun-dreds of dimensions. Many recent algorithms use concepts of proximity in order to nd outliers based on their relation-ship to the rest of the data. However, in high dimensional space, the data is sparse and the notion of proximity fails to retain its meaningfulness. In fact, the sparsity of high di-mensional data implies that every point is an almost equally good outlier from the perspective of proximity-based deni-tions. Consequently, for high dimensional data, the notion of nding meaningful outliers becomes substantially more complex and non-obvious. In this paper, we discuss new techniques for outlier detection which nd the outliers by studying the behavior of projections from the data set. 1