Home

Broadly speaking, 'Web Mining' has been defined as applying data mining techniques on web data to discover knowledge. Pattern discovery is the key component of the Web mining. it converges the algorithms and techniques from several research areas, such as data mining, machine learning, statistics and pattern recognition. 

Some researchers have applied mining techniques on the Web logs maintained by the servers so as to discover user access and traversal pattern [Zaiane 1998, Yi 1999 , Cooley 1997 , Zarkesh 1997 , Chen 1998 ]. For instance, Han et al. [Zaiane 1998] have minded information from web logs by implementing a MOLAP warehouse containing web log data and mining information off it. Krishnapuram et al. have developed new robust fuzzy clustering algorithms and used them on web logs, where as Shabhabi et al. [Zarkesh 1997] have developed clustering algorithm for user navigation patterns. Other researchers have interpreted web logs essentially as text files and applied phrasal mining techniques to the logs [Lent 1997] [Ahonen 1997].

In general, there are mainly four kinds of data mining techniques applied to the web mining domain to discover the user navigation pattern:

• Association Rule mining

• Sequential pattern

• Clustering

• Classification