A Study and Implementation of a Movie Recommendation System in a Cloud-based Environment

A Study and Implementation of a Movie Recommendation System in a Cloud-based Environment

Jaime Raigoza, Vikrantsinh Karande
Copyright: © 2017 |Pages: 12
DOI: 10.4018/IJGHPC.2017010103
OnDemand:
(Individual Articles)
Available
$37.50
Current Special Offers
No Current Special Offers
TOTAL SAVINGS: $37.50

Abstract

The availability of huge amounts of data in recent years have led users to being faced with an overload of choices. The outcome is a growth on the importance of recommendation systems due to their ability to solve this choice overload problem, by providing users with the most relevant products from many possible choices. For producing recommendations, things like a user's psychological profile, their browsing history and movie ratings from other users can be considered. To determine how strongly two user's behavior are related to each other, a Pearson correlation coefficient value is often calculated. In this paper, we study the recommendation system on a proposed cloud based environment to produce a list of recommended movies based on a user's profile information. Based on the Software-as-a-Service (SaaS) model implemented, we discuss the concepts such as collaborative filtering and content-based filtering. Given a MovieLens data-set, our results indicate that the proposed approach can provide a high performance in terms of precision, and generate more reliable and personalized movie recommendations, when given a greater number of movies rated by a user. An evaluation was done under minimal known data, which commonly leads to the cold-start problem.
Article Preview
Top

Recommender frameworks, being a subclass of data filtering framework tries to predict the choices that a client would make for an item (Ng, 2013). Recommendation systems typically produce a list of recommended items in one of two ways - through collaborative filtering or content-based filtering. The collaborative filtering (CF) approach works by collecting and maintaining user ratings for an item and comparing them to rating behavior of several other users for finding an appropriate match to make recommendations for the user. The content-based filtering approach utilizes a series of discrete characteristics of an item to recommend additional items with similar characteristics (Melville & Sindhwan, 2010).

Complete Article List

Search this Journal:
Reset
Volume 16: 1 Issue (2024)
Volume 15: 2 Issues (2023)
Volume 14: 6 Issues (2022): 1 Released, 5 Forthcoming
Volume 13: 4 Issues (2021)
Volume 12: 4 Issues (2020)
Volume 11: 4 Issues (2019)
Volume 10: 4 Issues (2018)
Volume 9: 4 Issues (2017)
Volume 8: 4 Issues (2016)
Volume 7: 4 Issues (2015)
Volume 6: 4 Issues (2014)
Volume 5: 4 Issues (2013)
Volume 4: 4 Issues (2012)
Volume 3: 4 Issues (2011)
Volume 2: 4 Issues (2010)
Volume 1: 4 Issues (2009)
View Complete Journal Contents Listing