Discovering knowledge by comparing silhouettes using K-means clustering for customer segmentation

A large amount of data is generated every day from different sources. Knowledge extraction is the discovery of some useful and potential information from data that can help to make better decisions. Today's business process requires a technique that is intelligent and has the capability to discover useful patterns in data called data mining. This research is about using silhouettes created from K-means clustering to extract knowledge. This paper implements K-means clustering technique in order to group customers into K clusters according to deals purchased in two different scenarios using evolutionary algorithm for optimization and compare silhouettes for different K values to analyze the improvement in extracted knowledge.