Collaborative Filtering Schemes Research Articles

A semantic approach to avoiding fake neighborhoods in collaborative recommendation of coupons through digital TV

Consumers are flooded with amounts of discount coupons, oftentimes for products that are far from their interests. This marketing custom is already rising on the Internet and is imminent in Digital TV, where the massive sending of coupons leads to their devaluation and consumer indifference. The computing capabilities of these media permit to alleviate this problem by means of recommender systems, which are very useful tools in application domains that suffer from information overload. However, current recommender systems overlook the diversity of products and services available in the market, which gives rise to forming fake neighborhoods in collaborative filtering strategies. In this paper, we apply semantic reasoning techniques to avoid such fake neighborhoods and, thereby, improve the recommendation process. Furthermore, taking advantage of the Digital TV medium, we propose matching the recommended coupons to TV contents semantically related with them, in order to increase their redemption.

One-and-only item recommendation with fuzzy logic techniques

Recommender systems anticipate users’ needs by suggesting items that are likely to interest them. Most existing systems employ collaborative filtering (CF) techniques, searching for regularities in the way users have rated items. While in general a successful approach, CF cannot cope well with so-called one-and-only items, that is: items of which there is only one single instance (like an event), and which as such cannot be repetitively “sold”. Typically such items are evaluated only after they have ceased being available, thereby thwarting the classical CF strategy. In this paper, we develop a conceptual framework for recommending one-and-only items. It uses fuzzy logic, which allows to reflect the graded/uncertain information in the domain, and to extend the CF paradigm, overcoming limitations of existing techniques. A possible application in the context of trade exhibition recommendation for e-government is discussed to illustrate the proposed conceptual framework.