In 2010, Web users ordered, only in Amazon, 73 items per second and massively contribute reviews about their consuming experience. As the Web matures and becomes social and participatory, collaborative filters are the basic complement in searching online information about people, events and products. This article provides an overview of the technical aspects characterizing recommendation systems. After providing a comprehensive definition of goods and users in the Web, we describe a classification of recommendation systems based on two families of criteria: how recommendations are formed and input data availability. The classification is presented under a common minimal matrix notation and is used as a bridge to related issues in the business and marketing literature. We focus our analysis in the fields of one-to-one marketing, network-based marketing Web merchandising and atmospherics and their implications in the processes of personalization and adaptation in the Web. Market basket analysis is investigated in context of recommendation systems.
- WSSC: webscience.org/2010/D.2.4 Statistical Analysis of the Web; webscience.org/2010/E.1.1.1 Goods in the Web
- ACM: H.3.3 Information Search and Retrieval