A Clustering and Associativity Analysis Based Probabilistic Method for Web Page Prediction

Abstract

Today all the information, resources are available online through websites and web page. To access any instant information about any product, institution or organization, users can access the online available web pages. In this work, a three stage model is provided for more intelligent web page prediction. The method used the clustering and associativity analysis with rule formulation to improve the prediction results. The CMeans clustering is applied in this prior stage to identify the sessions with high and low usage of web pages. Once the clustering is done, the rule is defined to identify the sessions with page occurrence more than average. In the final stage, the neuro-fuzzy is applied to perform the web page prediction. The result shows that the model has provided the effective derivation on web page visits.