MODIFIED K-MEDIOD ALGORITHM OF CLUSTERING FOR WEB USAGE MINING

web mining

World Wide Web is consisting of large amount of information and provides it different kind’s users in server. Due to increasing number of users access the web day by day, there is a need to analyses behavior of such user, in order to monitoring and improving the performance and throughput of website. Web usage mining is one of the parts of data mining applications which dealing with log files and extracting the useful information from web data. There are different phases included in web usage mining: Data pre-processing, discover pattern and pattern analysis. Among all of them data pre-processing is the most crucial and time consuming phase of web usage mining because without good quality of data it is difficult to identify pattern of user’s behavior. Pre-processing technique improves the quality and accuracy of the pattern mining algorithms. The existing system have done the pre-processing activities for reducing the size of the log file and to identify the unique users and sessions but existing system face scalability problem because web data increase day by day. The propose technique reduces the scalability problem and also improve the performance of web usage mining and pre-processing by using modified k-mediod clustering technique.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.