Efficient Collaborative Filtering based Recommendation System for Business Promotions Using Deep Neural Network
R.P. Jaia Priyankka1, S. Arivalagan2, P. Sudhakar3
1R.P. Jaia Priyankka, Research Scholar, Department of Computer Science, Annamalai University, Chidambaram (Tamil Nadu), India.
2Dr. S. Arivalagan, Assistant Professor, Department of Computer Science & Engineering, Annamalai University, Chidambaram (Tamil Nadu), India.
3Dr. P. Sudhakar, Assistant Professor, Department of Computer Science & Engineering, Annamalai University, Chidambaram (Tamil Nadu), India.
Manuscript received on 22 April 2019 | Revised Manuscript received on 01 May 2019 | Manuscript Published on 08 May 2019 | PP: 125-133 | Volume-7 Issue-5S3 February 2019 | Retrieval Number: E11240275S19/19©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: In the last decade, recommendation system (RS) has become popular due to its capability to foresee whether the specific customer would have preference for the item or not depending over the customer profile. Collaborative filtering methods in RS constructs the model after the consideration of the history of the user such as ratings given by the user to particular products, previously bought, wish list, etc. In addition, it also considers the identical decisions made by various users and then employs the model to determine the product or rating in which the user may be interested in. As the user’s rating plays a major part in collaborative filtering, it is needed to develop a classification model to classify the product reviews. In this paper, we introduce a collaborative filtering method using deep neural network (DNN) to classify the online produce reviews. Based on the classification of the reviews, the products will be properly recommended to the user. The proposed DNN model is validated using a set of four dataset collected from online product reviews from Amazon namely Canon dataset, iPod dataset, DVD and Nokia dataset. The experimental values proves that the DNN model is effective than the compared methods.
Keywords: Classification, Collaborative Filtering, Deep Neural Network, Recommendation System.
Scope of the Article: Neural Information Processing