Personalized interfaces based on recommender systems play a central role in the solution of big data problems. Recommender systems adopt data-mining and artificial-intelligence techniques to facilitate search in large amounts of digital information, and help users to identify the content that are likely to be more attractive or useful for them. Recommender systems infer such recommendations on the basis of different elements: popularity, demographic information about users, individual’s or community’s past preferences and choices, explicit ratings or comments, social networks, context of use. During the last years, recommender systems have seen an increasing adoption in various interactive services. The most famous success story of a recommender system is Netflix. The Netflix company launched in 2008 a competition (www.netflixprize.com) offering a 1 million dollar prize to anyone able to create a better recommendation system than the one adopted by Netflix itself for its video-streaming service.
This course explores the persuasiveness of recommender systems and presents several recommender algorithms, including the Netflix winner algorithm. For each algorithm, we investigate its quality in terms of accuracy and novelty of recommendations.
Showing posts 1 - 5 of 6. View more »