If you have ever bought something online you are familiar with recommendations for other products being generated for you. You buy the latest Dylan album and are recommended his previous back catalog, that kind of thing. Now conventional systems generate these suggestions by picking items that are like items that other users have purchased in the past. Professor Barry Smyth, a University College Dublin (UCD) scientist, has made a major breakthrough in online “recommender” systems and has been granted US and China patents on his system to improve online shopping and information.
Professor Smyth says his new technique will help existing recommender systems to produce recommendations that are both relevant to users and different from each other.
“One limitation is a tendency to produce sets of recommendations that are similar to each other”
The new system avoids very similar products being recommended together and allows more choices to be displayed.
This is a major research area in computer science and Irish universities are at the leading edge of the field. Netflix, the US online movie rental company, is using open innovation with a $1 million competition to develop the next generation of recommender systems.
Check out research by Professor Smyth and the team at Clarity – the Centre for Sensor Web Technologies
Bob’s New Album is pretty good though too..
