Distributed Web Usage Mining Based Recommender System in Big Data Analytics using Hybrid Firefly Algorithm
AC. Priya Ranjani1, M. Sridhar2
1AC. Priya Ranjani, Research Scholar, Department of Computer Science, Acharya Nagarjuna University, Guntur (Andhra Pradesh), India.
2Dr. M. Sridhar, Associate Professor, Department of Computer Applications, RVR & JC College of Engineering, Guntur (Andhra Pradesh), India.
Manuscript received on 05 February 2019 | Revised Manuscript received on 13 February 2019 | Manuscript published on 28 February 2019 | PP: 386-393 | Volume-8 Issue-4, February 2019 | Retrieval Number: D2697028419/19©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: One of the fast upcoming data mining disciplines that deal with large, unstructured complex data is Big data analysis. Web usage mining is a primary area of research that has been focusing on the valuable information derived from web server logs. Not having any explicit ratings of the users, the large data volume and its sparse nature have been posing challenges to the techniques of collaborative filtering with respect to performance and scalability. Techniques like clustering are dependent on the discovery of offline patterns from the user transactions and are used to improve scalability in terms of collaborative filtering but at reduced cost and recommendation accuracy. To improve the situation, this work has been taken up on the basis of nature inspired, meta heuristic algorithms Firefly and Teaching Learning Based Optimization (FA-TLBO). This FA-TLBO was hybridized using the K-Means algorithm (FA-TLBO with K-Means) in order to obtain optimal cluster centres. There were numerical experiments which indicated the fact that novel FA-TLBO with K-means was more efficient compared to TLBO algorithm.
Keyword: Big Data Analysis, Web Usage Mining, Recommender System, Clustering, K-Means Algorithm, Firefly Algorithm (FA) and Teaching Learning Based Optimization (TLBO).
Scope of the Article: Big Data Networking