Recommendation Engine

Across the world, people share an astonishing urge to absorb new information. This broad interest ranges from great events like the Big Bang and the start of our universe all the way down to the smallest peculiarities portrayed and posted by their neighbors.

To feed this unsatisfiable thirst for information, powerful search technologies have been developed and successfully deployed on the Web. However, these technologies, which once were our search companions, now often return millions of allegedly relevant results in an attempt to answer a simple question. Moreover, given the amount of results returned, it is again up to the user to select the best result from a huge list without the guarantee of finding what he is looking for.

Due to this exponential growth of data, it is again the user who needs to decide which search result to investigate further, which radio channel to listen to, which news item to read, which TV program to watch, etc. In the end, we will all find ourselves overloaded by the huge and never-ending information provisioning.

As often, the main underlying problem in all of these situations is choice. People need to choose a TV program, a radio station, a book, a Web site, a news item, a friend, etc. out of an increasingly large world of possibilities. Basically, too much choice inevitably leads to less satisfaction with the final choice, possibly inducing an aversion against the technologies providing it.

Therefore, the challenge of the future is to help people finding their way through the forest of choice. Instead of providing more options, possibilities and features, we need to introduce a smart pre-selection step which decreases the choice without losing the pick of the bunch. Ideally, such a system could revolutionize our lives by presenting exactly those television programs you want to watch, that radio station you want to listen to, the Web site you want to read or even the clothes you want to wear, the new car you want to buy in the colors of your liking or the food you want to eat. Such a system is called a recommendation engine.

Stoneroos has developed a TV program recommendation engine which is designed to recommend a fitting TV program selection for the user, or at least to support him in making a choice himself. The recommendation engine is a customizable system which builds on proven technology like among others ``Collaborative filtering" and ``Item-based filtering". To do so, the engine monitors the user's activities and behavior to build a user model. Such a user model represents a consolidated representation of the user including all his interests, favorites, likings and much more, in a context-sensitive setting. After all, people can have different needs in different situations. Given such a user model, the Stoneroos recommendation engine considers all available programs (can be regular broadcast, items in a VOD library, etc.) and creates a ranking showing the best fitting programs at the top. If necessary, the algorithm can be tweaked, by means of a given set of rules, to promote specific movies or programs.