Analysis and Evaluation of a Framework for Sampling Database in Recommenders

Analysis and Evaluation of a Framework for Sampling Database in Recommenders

Hodjat Hamidi (Department of Information Technology, Faculty of Industrial Engineering, K. N. Toosi University of Technology, Tehran, Iran) and Reza Mousavi (Department of Information Technology, Faculty of Industrial Engineering, K. N. Toosi University of Technology, Tehran, Iran)
Copyright: © 2018 |Pages: 17
DOI: 10.4018/JGIM.2018010103
OnDemand PDF Download:
$30.00
List Price: $37.50

Abstract

In this paper the authors proposed a database sampling framework that aims to minimize the time necessary to produce a sample database. They argue that the performance of current relational database sampling techniques that maintain the data integrity of the sample database is low and a faster strategy needs to be devised. The sampling method targets the production environment of a system under development that generally consists of large amounts of data computationally costly to analyze. The results have been improved due to the fact that the authors have selected the users that they had more information about them and they have made the data table denser. Therefore, by increasing the data and making the rating more comprehensive for all the users they can help to produce the more and better association rules. The obtained results were not that much suitable for Jester dataset but with their proposed methods the authors have tried to improve the quantity and quality of the rules. These results indicate that the effectiveness of the system greatly depends on the input data and the applied dataset. In addition, if the user rates more number of the items the system efficiency will be more increased.
Article Preview

1. Introduction

Recommender systems are an important facet of Internet-based sellers’ advertising and promotion strategies due to their ability to deliver shopping advice, stimulate consumers’ purchase desires and boost sales (Jannach et al., 2011). However, when managers introduce recommendation services, do they need to take into account that men and woman may react differently to the advice? This is important because advertising is the major way in which marketers communicate with different target segments in the traditional market, and recommendations have played a similar role in the e-commerce market. Moreover, for many years, gender has been considered to be the most useful basis for market segmentation because both segments are profitable and easy to target (Adomavicius et al., 2005). Consequently, managers must understand whether there are decision-processing differences between men and women in order to produce effective recommender system advice for each segment. Since that start, the field has advanced through both basic research and commercial development to the point where today recommender systems are embedded in a wide range of commerce and content applications (both online and offline), where recommender systems handbooks and texts have been published (e.g., Ricci et al., 2011; Wu et al., 2016; Kumar, 2016; Ye et al., 2016; Hamidi et al,2017), where universities are offering courses on recommender systems, and where there is a dedicated annual conference on the topic. The scope of recommender systems has also broadened; while the term originally grew out of work in collaborative filtering, it quickly expanded to include a broader range of content-based and knowledge-based approaches. While such systems are important, we limit our focus to recommender systems that are based on collaborative filtering, though many of the interface issues we discuss apply to recommenders based on different approaches. This limitation reflects both our own expertise and the practical limitations of addressing so broad a field in a single article. We do not attempt to offer a comprehensive review of past algorithmic research.

Indeed, there have been a number of thorough surveys that focus on the algorithms behind recommenders (Burke 2002; Ekstrand et al., 2011; ; Hamidi et al.,2017; Herlocker et al., 2004), and we refer the interested reader to them. Rather, we present an overview of the most important developments in the field that touch on the user experience of the recommender. By user experience we mean the delivery of the recommendations to the user and the interaction of the user with those recommendations. The user experience necessarily includes algorithms, often extended from their original form, but these algorithms are now embedded in the context of the application. Our review looks at research grounded in specific recommender systems and their evaluations, and stands in contrast to Knijnenburg et al. (2012) which approaches user experience from more of an experience-model and social-experimental approach. In the rest of this section we highlight the main directions of work in the early years of recommender systems, including the beginning of the shift away from thinking of recommenders as prediction engines to considering them in the context of user experience.

In this paper, we propose a very fast sampling method that maintains the referential integrity of the sample database intact. The sampling method targets the production environment of a system under development, that generally consists of large amounts of data computationally costly to analyze.

Complete Article List

Search this Journal:
Reset
Open Access Articles: Forthcoming
Volume 26: 4 Issues (2018): 1 Released, 3 Forthcoming
Volume 25: 4 Issues (2017)
Volume 24: 4 Issues (2016)
Volume 23: 4 Issues (2015)
Volume 22: 4 Issues (2014)
Volume 21: 4 Issues (2013)
Volume 20: 4 Issues (2012)
Volume 19: 4 Issues (2011)
Volume 18: 4 Issues (2010)
Volume 17: 4 Issues (2009)
Volume 16: 4 Issues (2008)
Volume 15: 4 Issues (2007)
Volume 14: 4 Issues (2006)
Volume 13: 4 Issues (2005)
Volume 12: 4 Issues (2004)
Volume 11: 4 Issues (2003)
Volume 10: 4 Issues (2002)
Volume 9: 4 Issues (2001)
Volume 8: 4 Issues (2000)
Volume 7: 4 Issues (1999)
Volume 6: 4 Issues (1998)
Volume 5: 4 Issues (1997)
Volume 4: 4 Issues (1996)
Volume 3: 4 Issues (1995)
Volume 2: 4 Issues (1994)
Volume 1: 4 Issues (1993)
View Complete Journal Contents Listing