The recommender systems, was introduced as a subclass of information filtering systems that seeks to predict the "preference" that a user would give to an item.
The most important methods of information filtering are:
Collaborative filtering approaches build a model from a user's past behavior (items previously purchased or selected and numerical ratings given to those items) as well as similar decisions made by other users. This model is then used to predict items (or ratings for items) that the user may have an interest in.
Content-based filtering approaches utilize a series of characteristics of an item in order to recommend additional items with similar properties. Recommender systems usually make use of either or both collaborative filtering and content-based filtering (also known as the personality-based approach). Leer mas...
DESCRIPTION
Nowadays, current recommender systems typically combine one or more above approaches with others recommender systems as knowledge-based systems , Multi-criteria systems or Optimization-based systems into a hybrid systems called multi-recommender systems.
The IIIA has experience in the following kind of recommender systems:
Knowledge-Based Systems are based on explicit knowledge about the item assortment, user preferences, and recommendation criteria (i.e., which item should be recommended in which context). These systems are applied in scenarios where Rating-based systems do not perform well due to the low number of available ratings.
A major strength of knowledge-based recommender systems is the non-existence of cold start problems. A corresponding drawback is a potential knowledge acquisition bottleneck triggered by the need to define recommendation knowledge in an explicit fashion. Knowledge-based recommender systems are well suited to complex domains where items are not purchased very often, such as apartments, cars, financial services, tourist destinations, etc.
Multicriteria systems are based on a multi-criteria rating setting, that is, users can provide ratings on multiple attributes of an item. The additional information provided by multi-criteria ratings could help to improve the quality of recommendations because it would be able to represent more complex preferences of each user. The task of recommender systems can be modelled as a multicriteria (multi-objective) optimization problem. In this sense the optimization techniques allow us to face complex item recommendation systems made up of different components with multiple attributes.
Optimization-based recommender Systems, are recommenders that use optimization techniques to search the best item for a user. It is used for recommend complex items, made up of different components with multiple attributes.
Argumentation-based recommender Systems. A significant problem of recommender systems is their inability to explain recommendations, resulting in turn in ineffective feedback from users and the inability to adapt to users’ preferences. Argumentation-based recommender Systems are recommender systems with the capability to interact with the user explaining its recommendations by means of arguments that the user can accept or answer with a counterargument.
Arguments play two different roles in day life decisions, as well as in the recommendation of more crucial issues. Namely, they help to explain and justify an already adopted recommender choice, or they help to select one or several alternatives. On the other hand counterargumentation allow the user to improve and personalize the recommender system.