what is a recommender system?

Recommender systems are usually classified into three categories: content-based, collaborative, and hybrid. Content-based recommender systems show the user items similar to the ones the user rated highly in the past. For example, a movie recommender system classifies movies based on genre, actors, general rating, and other characteristics. It then looks for other movies with classifications similar to movies the user has viewed and rated highly in the past. Over time, content-based systems learn about user taste and preferences either implicitly or explicitly. On the other hand, collaborative recommender systems show the user items that people with similar tastes and preferences have liked in the past. Amazon’s system for recommending books is an example of a collaborative recommender system. Finally, hybrid systems utilize a mix of both content-based and collaborative system technology. Hybrid systems can combine content-based and collaborative recommender systems in several ways. Hybrid systems can apply both methods separately and merge the predictions from both systems, or incorporate some characteristics of one approach into the other. This combination is used to avoid some of the limitations of content-based and collaborative recommender systems.

what is an anti-recommender system?

Art I Don’t Like is a web-based interactive art experience that provides personalized content to users. The user is presented with a set of art images and is prompted to choose the pieces that they find visually appealing. Our “anti-recommender” algorithm analyses the selected images and computes similarity scores. The system then shows the user a work of art with a low similarity score, that is, a work that the user might not like. The underlying technology is a neural network that classifies the art based on artist and genre. Future work will include other characteristics. This system will expose users to a broad range of art and shed light on how recommendations are made. Users will be encouraged to leave feedback about why they like or dislike the art they have been shown. Art I Don’t Like gives users a digital space to view and interact with art that they may not be familiar with.