Recommender Technologies and Emerging Applications

Recommender Technologies and Emerging Applications

Young Park (Bradley University, USA)
Copyright: © 2018 |Pages: 11
DOI: 10.4018/978-1-5225-2255-3.ch163
OnDemand PDF Download:
$30.00
List Price: $37.50

Chapter Preview

Top

Background

Since the first major recommender systems emerged in the mid-1990s (Resnick & Varian, 1997), a large number of recommender systems have been developed and used in a wide range of e-commerce environments and improved by continuing research.

A typical recommender system provides users with personalized recommendations of items such as goods, services or information to guide users to find items that are relevant to them. Recommendations are based on past and present profiles of users with respect to items. The personalized recommendation problem can be described as follows:

Given a target user, produce personalized recommendations of items relevant to the target user.

To solve this recommendation problem, a recommender system generally uses three types of data—data about the users (U_data), data about the items such as goods, services or information (I_data), and data about the relevance (such as rating, evaluation, purchase, or interest) relation between the users and the items (R_data):

Key Terms in this Chapter

Electronic Commerce: Activities of a traditional commerce process by using information and communication technologies through the Internet and intranets.

Item-to-Item Collaborative Filtering: Collaborative filtering method that is based on similar items and recommends a list of items that are similar to the items that were given good relevance feedback by the target user.

Collaborative Recommender Systems: Recommender systems that recommend items through user collaborations and are the most widely used and proven method of providing recommendations. There are three types: user-to-user collaborative filtering based on user-to-user similarity, item-to-item collaborative filtering based on item-to-item similarity, and latent factor-based collaborative filtering based on user-item matrix factorization.

Content-Based Recommender Systems: Recommender systems that are based on content of items and recommend a list of items with similar content to that of the items that were given good feedback by the target user.

Personalized Recommendation Problem: Given a target user, produce personalized recommendations of items such as goods, services or information for the target user.

Recommender Systems (Recommendation Systems): Systems that provide users with personalized recommendations of items such as goods, services or information and thus help users find relevant items in the information overload.

Hybrid Recommender Systems: Recommender systems that recommends items by combining two or more methods together, including the content-based method, the collaborative filtering-based method, the demographic method and the knowledge-based method.

Latent Factor Model-Based Collaborative Filtering: Collaborative filtering method that is based on latent factor models such as matrix factorizations and recommends a list of items that other user gave relevance feedback similar to that provided by the target user.

User-to-User Collaborative Filtering: Collaborative filtering method that is based on similar users and recommends a list of items that other user gave relevance feedback similar to that provided by the target user.

Complete Chapter List

Search this Book:
Reset