E-Commerce Recommendation Systems

E-Commerce Recommendation Systems

Konstantinos Markellos (University of Patras, Greece), Penelope Markellou (University of Patras, Greece), Aristotelis Mertis (University of Patras, Greece) and Angeliki Panayiotaki (University of Patras, Greece & Hellenic Ministry of Economy & Finance, Greece)
Copyright: © 2009 |Pages: 9
DOI: 10.4018/978-1-59904-845-1.ch024
OnDemand PDF Download:
$30.00
List Price: $37.50

Abstract

In the last decade electronic and wireless technologies have changed the way companies do business forever. E-commerce (electronic commerce) and e-business (electronic business) feature as extremely dynamic economic sectors and at the same time, as the most appealing ways of beginning or expanding a business activity. Successful companies today recognize these technologies and the Internet as mainstream to business success. Indeed, their future will continue to be promising to companies seeking means for cost cutting, enhanced productivity, improved efficiency, and increased customers’ satisfaction. On the other hand, this networked economy is notably characterized by the impersonal nature of the online environment and the extensive use of IT (information technology), as opposed to face-to-face contact for transactions.
Chapter Preview
Top

Introduction

In the last decade electronic and wireless technologies have changed the way companies do business forever. E-commerce (electronic commerce) and e-business (electronic business) feature as extremely dynamic economic sectors and at the same time, aas the most appealing ways of beginning or expanding a business activity. Successful companies today recognize these technologies and the Internet as mainstream to business success. Indeed, their future will continue to be promising to companies seeking means for cost cutting, enhanced productivity, improved efficiency, and increased customers’ satisfaction. On the other hand, this networked economy is notably characterized by the impersonal nature of the online environment and the extensive use of IT (information technology), as opposed to face-to-face contact for transactions.

Since Internet technologies and infrastructures to support e-commerce are now in place, attention is turning to psychological factors that affect its acceptance by online consumers and their perceptions of online transactions. One such factor is individuality of e-customers, seen to be key to the proliferation of e-commerce. The demand for better products and services has been a pressing need. The question is how easily Internet users become e-customers and which are the internal “mechanisms” and external factors that participate in an e-purchase. The problem arises from the fact that the shoppers have varying needs, preferences, and background. At the same time, they are confronted with too many options and information that they have to deal with, the majority of which is often irrelevant to their needs and interests. In most cases, search engines are used for filtering pages according to explicit users’ queries. However, their results are often poor since the produced lists are long, unmanageable, and contain irrelevant pages (Middleton, De Roure, & Shadbolt, 2004).

Currently, successful e-commerce strategies have focused on personalization technologies and opportunities. According to Personalization Consortium (2006):

“personalization is the combined use of technology and customer information to tailor electronic commerce interactions between a business and each individual customer”. In other words, it means “gathering and storing information about web site visitors and analyzing this information in order to deliver the right content in a user-preferred form and layout.” (Braynov, 2003)

Personalization is expected to be one means for pushing e-commerce and e-business forward. In this direction, the recent web technological advances help online companies to acquire individual customer’s information in real-time and with low cost. Based on this information, they construct detailed profiles and provide personalized e-services. Thus, e-shops have now greater potential for increasing customer satisfaction, promoting customer loyalty, establishing one-to-one relationships, and consequently for return on investment.

The most popular forms of personalization are recommendation or recommender systems (RSs) (Adomavicius & Tuzhilin, 2005). They have emerged in the middle of 1990’s and from novelties used by a few Websites have changed to important tools incorporated to many e-commerce applications (e.g., Amazon.com, eBay.com, CDNow.com). Specifically, these systems take advantage of users’ and/or communities’ opinions/ratings in order to support individuals to identify the information or products most likely to be interesting to them or relevant to their needs and preferences.

In this chapter, we investigate the way RSs support e-commerce Web sites in their attempt to convert visitors to customers. We present the background field, compare the latest RSs and describe a general process for RSs. Finally, we illustrate the future trends and challenges and discuss the open issues in the field.

Key Terms in this Chapter

Collaborative Filtering: It is the method of making automatic predictions (filtering) about the interests of a user by collecting taste information from many users (collaborating).

Content-Based Filtering: It uses product features and recommends products to users that have similar features with those they rated highly during the past.

Demographic Filtering: It employs demographic data (e.g., age, profession) to infer recommendation rules based on stereotypes.

Recommendation System: It is a program which attempt to predict items (movies, music, books, news, web pages, etc.) that a user may be interested in based on various information, for example demographics, transaction history, navigation, and so forth.

Personalization: It is a set of techniques and services that aim to solve the information overload problems Web users face, by providing them with what they want or need, without having to ask (or search) for it explicitly.

Hybrid Approaches: It combines various methods to produce recommendations in order to combine the robustness and eliminate the drawbacks of the individual techniques.

Complete Chapter List

Search this Book:
Reset