A Proficient Web Recommender System using Hybrid Possiblistic Fuzzy Clustering and Bayesian Model Approach

Abstract

In day to day life, the process of projecting the correct information to the authorized person is more difficult, which makes complexity to the decision making process. Web Page Recommendation Systems (WPRS) used in various fields to identify the customer needs and to help the users to take appropriate decisions over the service or product according to his/her preference. The group of users with similar preference will be identified by using Possibilistic Fuzzy C-Means (PFCM) algorithm with an S3I Similarity Measure (SM). The proposed method will determine the gain and loss of the web users based on the web directories which can be modified by using Relevance Feedback Bayesian Network (RFBN) technique. The experimental results are conducted on the MNSBC dataset and the outcomes are compared with the existing methods like Singular Value Decomposition (SVD) methods. The method predicts the accuracy up to 85% when compared with the existing methods and the outcome results proved the effectiveness of the PFCM -RFBN method.

Query Recommendation for Search Engine Results Using Machine Learning

“…We developed a search engine in such a way that, when the user gives a search in form of keywords or any ordinary sentences, it provides a vast amount of information in many websites instead of one. Our search engine [10] gives results based on what the user requires. After the search is given, it takes user to a page where the queries are recommended in websites like Google, Yahoo, and Bing and so on.…”