Evaluating Prediction Accuracy, Developmental Challenges, and Issues of Recommender Systems

Evaluating Prediction Accuracy, Developmental Challenges, and Issues of Recommender Systems

J. Sharon Moses, L.D. Dhinesh Babu
Copyright: © 2018 |Pages: 19
DOI: 10.4018/IJWP.2018070105
OnDemand:
(Individual Articles)
Available
$37.50
No Current Special Offers
TOTAL SAVINGS: $37.50

Abstract

Modern ways of living have made the people to depend on internet services for everything. The mounting information from various sources like social media, implicit and explicit information, user's geographical location, and the internet of things had increased the need of a recommender system. From e-governance to e-shopping, a recommender system helps people in finding the needed item or information and also boosts sales in the market of those items. Though many studies elaborate about recommendation systems, challenges in developing the recommendation systems, prevailing issues of recommendation systems and discussions on prediction accuracy are not detailed in any of the earlier works. Therefore, in this article, in order to increase the accuracy of the recommender system, the developmental challenges and issues in constructing recommender systems and for evaluation metrics in prediction accuracy are identified and detailed.
Article Preview
Top

2. Literature Review

The advancement of web made people to comprehend that finding or even distinguishing the items among the huge number of item isn't a simple errand. In this way, different techniques are started to assist the human in finding the item that they are searching for. This scenario leads to the development of syntactic search engine. This search engine filtered user needed webpage from numerous webpages. This strategy for seeking requested webpage yielded numerous numbers of website pages in which some are applicable and some unessential to the user query. Following this strategy tapestry the first framework with the substance of recommender strategy is invented by Xerox Palo Alto Research Centre in the year 1992 (Goldberg, Nichols, Oki, & Terry, 1992). In this system, the contents of the mail and its metadata information about author and notations are stored. Tapestry was able to query the textual information, metadata and even notation queries and this methodology of filtering information later known as pull-active collaborative filtering (Konstan & Riedl, 2003).

Complete Article List

Search this Journal:
Reset
Volume 15: 1 Issue (2024): Forthcoming, Available for Pre-Order
Volume 14: 2 Issues (2022): 1 Released, 1 Forthcoming
Volume 13: 2 Issues (2021)
Volume 12: 2 Issues (2020)
Volume 11: 2 Issues (2019)
Volume 10: 2 Issues (2018)
Volume 9: 2 Issues (2017)
Volume 8: 1 Issue (2016)
Volume 7: 2 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