Publication Type : Journal Article
Publisher : International Journal of Pure and Applied Mathematics
Source : International Journal of Pure and Applied Mathematics, Volume 119, p.247-253 (2018)
Url : https://acadpubl.eu/hub/2018-119-16/1/25.pdf
Keywords : Collaborative filtering, content based filtering, Cosine similarity, E-commerce, Pearson correlation coefficient
Campus : Amritapuri
School : Department of Computer Science and Engineering, School of Engineering
Department : Computer Science
Verified : Yes
Year : 2018
Abstract : In the recent advancement of e-commerce, most of the populace in the world are using the World Wide Web for the retrieval of information and to perform various transactions through internet. This has led to the increase in the complexity of information retrieval and thereby creating hurdles on efficient and fast filtering of information. To overcome the above problem, and to help the online readers to handle huge volume of data, a new method of information filtering has to be created. In this paper we present a new hybrid filtering approach which is the combination of collaborative and content based filtering. Collaborative Filtering is the method of matching people who have similar interest, which is done by collecting desirous information from many users using Pearson Correlation Coefficient. Content Based Filtering uses Cosine Similarity for analyzing the content of the user profile and the past browsing history maintained for each user. We present design of Adaptive Web Service Selection Framework that makes use of automated approach that systematically integrates all available training information such as past user, user similarity ratings as well content of user-paper rating, paper-user rating and user browsing history. The vital solution of our approach is simple relative frequency percentage bar to illustrate the combined approach which creates the most accurate web services recommendation to the individual user. The system is able to absorb the result of both filtering technique of information theories and it can be adopted for better and efficient recommendation. The results of this system reveals the fact that is able to dynamically offer recommended services based on end user’s interest.
Cite this Research Publication : S. Subbulakshmi, Rahul Varma U., and Nair, S., “PLING Adaptive Opportunity Checking of Web Service with Recommendation System”, International Journal of Pure and Applied Mathematics, vol. 119, 16 vol., pp. 247-253, 2018