Decision Trees and Recommender Systems - Data Mining with Decision Trees: Theory and Applications - page 251

Chapter 16

Decision Trees and
Recommender Systems

16.1 Introduction

Recommender Systems (RS) are considered to be a very popular research
area as they offer users useful and interesting items that increase both
the seller's profit and the buyer's satisfaction. They contribute to the
commercial success of many on-line ventures such as Amazon.com and
NetFlix. Examples of recommended items include movies, web pages, books,
news items and more. Often a RS attempts to predict the rating a user will
give to items based on his or her past ratings and the ratings of other
(similar) users.
RSs are primarily directed towards individuals who lack sucient
personal experience or competence to evaluate the potentially overwhelming
number of alternative items that a Websitemay offer. A case in point is a
topic recommender system that assists users to select a topic to read. In
the popular Website, Amazon.com, the site employs an RS to personalize
the online store for each customer. Since recommendations are usually
personalized, different users or user groups receive dissimilar suggestions.
In addition, there are non-personalized recommendations. These are much
simpler to generate and are normally featured in magazines or newspapers.
Typical examples include the top ten selections of books, CDs etc. While
they may be useful and effective in certain situations, these types of non-
personalized recommendations are typically not the ones to be addressed
by RS research.
In their simplest form, personalized recommendations are offered as
ranked lists of items. RSs try to predict the most suitable products
or services based on the user's preferences and constraints. In order

251