Abstract
Among thousands of alternatives, most of the time online customers cannot easily decide on which product to purchase or service to utilize. In order to assist online customers in their decision-making process, business owners have started to make their online platforms more intelligent by enhancing their platforms with intelligent recommender systems. Recommender systems, also known as recommender agents or intelligent agents, are intelligent software that provide easily accessible, personalized, highly relevant, and high-quality recommendations to customers in various online platforms. This chapter discusses different types of recommender systems and provides use case examples of recommender systems in various e-commerce platforms. This chapter shows how recommender systems make life easier for online customers in the constantly developing and growing internet environment. This chapter also discusses the challenges posed by recommender systems to online customers.
TopClassification Of Recommender Systems
There are six main types of recommender systems (Fig. 1) which are collaborative filtering recommender systems, content-based recommender systems, knowledge-based recommender systems, utility-based recommender systems, demographic based recommender systems and hybrid recommender systems. The following paragraphs explains each of these six different recommender systems types.
Figure 1. Classification of Recommender Systems
Key Terms in this Chapter
Machine Learning: It is a data analytics technique that uses algorithms and statistical models to teach computing system to perform a specific task. Rather than relying on explicit instructions, machine learning relies on patterns and inferences.
Data Mining: An interdisciplinary field that combines computer science and statistics with an overall goal to discover patterns in very large data sets and later turn them to valuable information that can be used by decision makers.
Recommender systems: Intelligent software that aims to predict users' interests and recommend products or services that quite likely are interesting for them.