ABSTRACT

In this study we uses an approach for increasing web performance by analyzing and predicting the user behavior from user access log , identifying the missing paths in the logs and completing the same using a web structure so as to enhance the accuracy of web usage mining. This paper uses a simulated example to compare the result of the Pre-fetched pages after completing the missing paths in the logs using web structure and if this paths are not completed. The result shows the accuracy of the predicted and pre-fetched pages has improved after completing the missing paths in the logs. This paper uses Markov Model 1st order and 2nd order to predict most frequently accessed pages.