Abstract
Web usage mining is application of data mining. Web Usage Mining is the automatic discovery of user access pattern from web servers. Web usage mining is consists of preprocessing, pattern discovery, pattern analysis. Web prediction is a classification problem which attempts to predict the most likely web pages that a user may visit depending on the information of the previously visited web pages. In this paper emphasizes is given on the user Behaviour using web log file prediction using web log record, click streams record and user information. Here, two different clustering techniques, namely Fuzzy C-Means Clustering algorithms and Markov model has been investigated to predict the webpage that will be accessed in the future based on the previous action of browsers behavior. But prediction of future request of the user mainly concern with its accuracy and efficiency. The discovered patterns can be used for better web page access prediction.Prediction model are better prediction of next web page the user want to visit. Using web page access prediction, the right advertisement will be placed in the website according to the users' browsing patterns.In Web page prediction, the next action corresponds to predicting the next page to be visited. The previous actions correspond to the previous pages that have already been visited.