Mining of Web Logs Using Preprocessing andClustering

The data pre-processing plays a major role in efficient mining process as Log data is normally noisy and indistinct. In data pre-processing method the rebuild of session and paths are going to complete by annexing lost pages. Additionally the transaction which explains the behaviour of users made accurate in pre-processing by calculating the time taken by the user to view particular page is accessed in the form of byte rate. By using web clustering various types of object can be clustered into different groups. The belief function similarity measures in algorithm include the clustering task by Dempster – Shafer’s theory. The main aim of this work is to achieve pre-processing and clustering of web log and to improve the website performance