Please enable JavaScript.

Coggle requires JavaScript to display documents.

Clustering - Coggle Diagram

- - - - Selection of data from a set of operational data needs to be done before the stage of extracting information in KDD begins.
    - - in this process we perform data cleaning before the data mining process can be carried out and also data enrichment or other information needed for KDD
    - - Coding is the process of transformation of data that has been selected, so the data is suitable for the data mining process.
    - - process of finding interesting patterns or information in selected data using certain techniques or methods.
    - - At this stage, checks are carried out whether the patterns or information found contradict the facts or hypotheses that existed previously.
- - - - This method does a grouping by first selecting one basic object that will be used as the initial value of the cluster
    - - In principle, the same as the sequential threshold procedure, only the selection of several initial cluster objects at once and then merging objects into them simultaneously.
    - - the development of the two methods above by optimizing the placement of objects in exchange for other clusters with the consideration of optimization criteria.
  - - - This method starts with the fact that each object forms its own cluster.
    - - The divisive method is the opposite of the agglomerative method. This method first starts with a large cluster that includes all observations (objects).