Clustering analysis is the task of grouping a set of objects in such a way that objects in the same group (cluster) are more similar than those in other clusters. It is one of the subjective modeling techniques widely used in the industry. One example of its usage is segmenting customer portfolios based on demographics, transaction behavior, or other behavioral attributes. Clustering generates natural clusters and is not dependent on any of the driving objective functions. Once the clustering does initial profiling of the portfolio, the objective modeling technique can be used to build a specific strategy.
There are a number of clustering algorithms such as hierarchical clustering, k-means clustering, spectral clustering, DBSCAN and so on. This recipe shows how to detect an anomaly from the network data based on the clustering technique.