Name  Comments on Applicability  Reference 

Hierarchical Clustering   (N1) combination of clusters are formed to choose from.
 Expensive and slow. n×n distance matrix needs to be made.
 Cannot work on very large datasets.
 Results are reproducible.
 Does not work well with hyperspherical clusters.
 Can provide insights into the way the data pts. are clustered.
 Can use various linkage methods(apart from centroid).


kmeans   Prespecified number of clusters.
 Less computationally intensive.
 Suited for large dataset.
 Point of start can be random which leads to a different result each time the algorithm runs.
 Kmeans needs circular data. Hyperspherical clusters.
 KMeans simply divides data into mutually exclusive subsets without giving much insight into the process of division.
 KMeans uses median or mean to compute centroid for representing cluster.


Gaussian Mixture Models   Prespecified number of clusters.
 GMs are somewhat more flexible and with a covariance matrix we can make the boundaries elliptical (as opposed to Kmeans which makes circular boundaries).
 Another thing is that GMs is a probabilistic algorithm. By assigning the probabilities to data points, we can express how strong is our belief that a given data point belongs to a specific cluster.
 GMs usually tend to be slower than KMeans because it takes more iterations to reach the convergence. (The problem with GMs is that they have converged quickly to a local minimum that is not very optimal for this dataset. To avoid this issue, GMs are usually initialized with KMeans.)


DBSCAN   No prespecified no. of clusters.
 Computationally a little intensive.
 Cannot efficiently handle large datasets.
 Suitable for noncompact and mixedup arbitrary shaped clusters.
 Uses densitybased clustering. Cannot work well with density varying data points.
 Not effected by noise or outliers.

