How to use recommender systems in e-business domains

Recommender systems (RS) were developed by research as a means to manage the information retrieval problem for users searching large databases. Recently they have become very popular among businesses as online marketing tools. Several online companies base their success on these systems, among other conditions. By looking at the last decades, the research on RS can be summarized into two main streams. The first research stream is focused on technical aspects of the algorithms and on identifying new ways to make them more accurate, while the second stream is focused on the effects of RS on customers. Therefore, we can draw several indications from the research on RS about the mistakes that companies should avoid when using RS. In this work we conduct an extensive literature and industrial review and we identify some crucial points managers should mind when developing a RS in order to make it as effective as possible in real world applications, or at least to avoid making it a failure