Saturday, 8 September 2018

Clustering Analysis in Data Science

Introduction of Clustering

A Cluster is a group of servers and other resources that act like a single system and enable high availability and, in some cases, load balancing and parallel processing.  


What is it?
  • Divides data into groups (clusters or segments or partitions)
  • Unsupervised learning
Why do this?
  • For better understanding. Examples:
  • Marketing/Sales. know your customer.
  • Communicating information
  • Biology,Climate, Medicine, etc.
For some Utility.Mainly as precursor to further Data Analysis.


Where is it Used?
  • Amazon    (Recommendation System)
  • Netflix      (Recommendation Movies)
  • Flickr        (Recommendation Photo's)
How business use Clustering
  • Retailer Store
  • Banking
  • Insurance Companies

Types of Clustering and Cluster

Types of Clustering
  • Exclusive Clustering
  • overlapping Clustering
  • Hierarchical Clustering
Exclusive Clustering :-
  • Hard Clustering
  • Data point/ Item belong exclusively to one cluster
  • For example : K-means Clustering
  
Overlapping Clustering :-
  • Soft Cluster
  • Data point/Item belong to multiple cluster
  • For example : Fuzzy/ C-Means Cluster
Hierarchical Clustering :-
Types of Cluster
  • Well Separated
  • Prototype Based
  • Graph Based
  • Density Based

No comments:

Post a Comment

Popular Posts