Comparison of Classification Modelling Algorithms in Web Usage Mining

Abstract

Web Usage Mining (WUM) includes
identification of patterns used and has various
empirical approaches. It has evolved into a strong area
of analysis in data mining specialization due to critical
ethics. It is composed of three stages such as Pre-
Processing, Pattern Discovery, Pattern Analysis. Here
an experimental differentiation among supervised
learning algorithms: Decision Tree Classifier, Naive
Bayes Classifier, K Nearest Neighbour Classifier and
Support Vector Machine (SVM) is discussed.
Classification is one among the mining methods which
is concerned about the web dominion. It is used to
envision definite class of a particular data set in order
to categorize the data to predefined classes. The
classifier is a purpose which is used to depict new data
to already defined group or category. This paper
compares the various classification modelling
techniques used to classify web users.