Prediction of User’s Next Web Page Request By Hybrid Technique

The problem of predicting user’s web page request is gaining importance due to the increase in the demand of world wide web; recently Markov models are widely used for this purpose. Markov models found major application in this area different order markov models are used for providing different level of accuracy to the prediction .This paper focuses on different techniques used for predicting user’s request and also introduced the hybrid technique for web page request prediction that is the combination of markov model and the nearest neighbor model. The web is a large source of information that can be turned into knowledge. That part of knowledge concerns the usage of web itself and is valuable to website and organization of websites. Web mining is the application of data mining techniques to discover patterns from the web. Web logs contain information about web server request and response. In this paper we propose a Hybrid web page prediction technique by which we improve the performance of web page access time. In this technique combination of nearest neighbour algorithm and markov model are applied. More over we propose a technique for log writing and managing the logs, by which we easily find the pattern of required data. Keywords—Hybrid Technique, Markov model , PLSA,SVR, SVM ,World wide web.