With the rapid development into the new research application of outlier detection has been studied broadly in Machine Learning. Many traditional outlier detection techniques do not work well in such an environment. Therefore, developing up-to-date outlier detection methods becomes urgent tasks. Various methods for detecting different kinds of outliers in high-dimensional data sets from two different perspectives, i.e. detecting the outlying aspects of a data object and detecting outlying data objects of a data set. In this proposed work, here we present an integrated methodology Local outlier factor (LOF) and Parzen window technique for the identification of outliers which is suitable for datasets with higher number of variables than observations for high dimensional dataset. Our integrated methodology is that the outliers can be detected without training datasets or prior knowledge about the underlying process that produces the dataset. Therefore, the local density based outliers can be computed very efficiently.