Abstract: Lately, recommender systems (RS) have offered a remarkable breakthrough to users. It lessens the user time cost thereby delivering faster and better results. After purchasing a product there are recommendations according to the different comments provided by users. Within a short span of product utilization and quality, the users receive a product recommendation. But this doesn’t work out good so as to make it much better;feedbacks, commands and reviews are fetched on the basis of in-depth commands, globally like and normal keys. Recommendation systems are crucially important for the delivery of personalized product to users. With personalized recommendation to product, users can enjoy a variety of targeted recommendations such as online product; the current paper suggests hybrid recommendation system (HRS) that makes use of rating and review to recommend any product to user. The main objective of this paper is to personalize recommendation of product that have become extremely effective revenue drivers for online shopping business. Despite the great benefits, deploying personalized recommendation services typically requires the collection of users’ personal data for processing and analytics, which undesirably makes users. To implement product recommendations following are incorporated that is retrieving personal data, Logical Language based Rule Generation (LLRG), ranking and Hybrid recommendation system. The stages in the suggested recommendation system include, Data Gathering, preprocessing, filtering and Ranking. The Ranking algorithm ranks the products in relation to the sales count. The top list displays the product having greatest count number. In the LLRG strategy, the logic rule generation methodology retrieves useful and mandatory data from reviews, commands, products original state and thereafter comes the recommendation. The HRS enforces two techniques, namely, location based and the other being heterogeneous domain based. Also the recommendations presented to the user are in context to the user’s activities, choices and conduct that are in accord with user’s personal likings and aids in decision making. When comparing the outcome, it is clear that the suggested method is superior than the traditional with regard to clarity, effective recommendation and coverage rate. It’s evaluated that Hybrid Recommendation System yields in greater results compared with rest of the existing recommendation techniques. We, also identity to some future research directions.

R. Shanthi and S.P. Rajagopalan, “A Personalized Hybrid Recommendation Procedure for Internet Shopping Support” International Journal of Advanced Computer Science and Applications(IJACSA), 9(12), 2018. http://dx.doi.org/10.14569/IJACSA.2018.091252

@article{Shanthi2018,
title = {A Personalized Hybrid Recommendation Procedure for Internet Shopping Support},
journal = {International Journal of Advanced Computer Science and Applications},
doi = {10.14569/IJACSA.2018.091252},
url = {http://dx.doi.org/10.14569/IJACSA.2018.091252},
year = {2018},
publisher = {The Science and Information Organization},
volume = {9},
number = {12},
author = {R. Shanthi and S.P. Rajagopalan}
}