Prediction Model on Web Mining |
Author(s): |
Pratik J. Bhise , tulsiramji gaikwad patil college of engg & technology; Mithun Funde, tulsiramji gaikwad patil college of engg & technology; Prajakta Ramteke, tulsiramji gaikwad patil college of engg & technology |
Keywords: |
Web Usage Mining, Markov models, Bayesian theorem, Prediction |
Abstract |
Because of the rapid growth of the word-wide-web, the problem of predicting a user’s browsing behavior on a web-site has gained important and the need is personalize and influence a user’s browsing experience. For solving this problem Markov models and its variations have been found. Personalization, building proper websites, promotion, getting marketing information, and forecasting market trends etc, the prediction result can be used. By using Markov model the users’ browsing behaviors can be predicted at category level. Probability of present and infer users’ browsing behaviors at webpage level by applying the Bayesian theorem. The system can effectively filter the possible category of the websites by Markov models and predict websites accuracy by the Bayesian theorem. In this paper we present different techniques for prediction of users’ browsing behaviors and intelligently selecting parts of different order Markov model. The resulting model has improved prediction accuracy and reduced state complexity. |
Other Details |
Paper ID: IJSRDV4I10837 Published in: Volume : 4, Issue : 1 Publication Date: 01/04/2016 Page(s): 739-743 |
Article Preview |
|
|