This document discusses outlier detection in high dimensional data through integrated feature selection algorithms. It defines outliers and lists some applications of outlier detection. It then discusses challenges of detecting outliers in high dimensional space due to the "curse of dimensionality". The document proposes integrating feature selection algorithms with outlier detection methods to address this issue. It describes the key steps of feature selection, including subset generation, evaluation, stopping criteria, and result validation. Finally, it suggests that filter models are preferred over wrapper models for feature selection in high dimensional data due to lower computational costs.