Enhanced Recommendation System for E-commerce Applications
S. Sumanth1, Pradeep Kumar2
1Mr. Pradeep Kumar, Assistant Professor in Computer Science Department of Ramaiah Institute of Technology. Bengaluru, Karnataka, India.
2Mr S. Sumanth. Pai, pursuing M-Tech in CSE from MSRIT, obtained BE in CSE from VTU, Bengaluru, Karnataka, India.
Manuscript received on 25 June 2019 | Revised Manuscript received on 05 July 2019 | Manuscript published on 30 July 2019 | PP: 473-478 | Volume-8 Issue-9, July 2019 | Retrieval Number: H6914068819/19©BEIESP | DOI: 10.35940/ijitee.H6914.078919
Open Access | Ethics and 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: Recommendation algorithms play a quintessential role in development of E-commerce recommendation system, Where in Collaborative filtering algorithm is a major contributor for most recommendation systems since they are a flavor of KNN algorithm specifically tailored for E-commerce Web Applications, the main advantages of using CF algorithms are they are efficient in capturing collective experiences and behavior of e-commerce customers in real time, But it is noted that , this results in the phenomenon of Mathew effect, Wherein only popular products are listed into the recommendation list and lesser popular items tend to become even more scarce. Hence this results in products which are already familiar to users being discovered redundantly, thus potential discovery of niche and new items in the e-commerce application is compromised. To address this issue , this paper throws light on user behavior on the online shopping platform , accordingly a novel selectivity based collaborative filtering algorithm is proposed with innovator products that can recommend niche items but less popular products to users by introducing the concept of collaborative filtering with consumer influencing capability. Specifically, innovator products are a special subset of products which are less popular/ have received less traction from users but are genuinely of higher quality, therefore, these aforementioned products can be captured in the recommendation list via innovator-recognition table, achieving the balance between popularity and practicability for the user
Keywords: Niche Products, Collaborative Filtering (CF), Innovator Products, Recommender System.
Scope of the Article: E-Commerce,