MOVSOM Research Lab

The virtual lab of

We're two enthusiastic students of the computer science, the mathematics and the joy of data mining and the wonders of artifical neural networks that are very interested in recommender systems, specifically recommender systems for movies.

Our hopes are to continue researching recommender systems (which we find fun!) and eventually move projects over to our company MOVSOM™ Five by Five for sale.

Movie clustering using the self-organizing map: MOVSOM

2004-06-19 The aim of this report is to investigate whether it is possible to determine whether two or more movies are alike. We will describe two approaches; one where we only use the movie's plot description and one where we use preselected keywords that are significant for the movie.

The MOVSOM-I Paper.

MOVSOM-II - analyzis and visualization of movieplot clusters

2004-07-27 Clustering movieplots and visualizing the results in a user friendly way that makes it possible for a user to select a movie they have seen and then be recommended movies that are similar to that movie in some way.

Read the MOVSOM-II Paper.

The use of Self-Organizing Maps in Recommender Systems

2006-08-22 Our thesis about recommender systems, and the different approaches recommender systems use to solve the information overload problem.

Read the SOMRS Paper.

MOVSOM - the Self-Organizing Map for Movie Exploration

State of the Art Highly Interactive Visual Movie Recommender System. MOVSOM provides Visual Recommendations of movies and encourages exploration of the entire movie recommendation space.

MOVSOM builds upon the ingenious Teuvo Kohonen's Self Organizing Map algorithm. Be sure to also check out their WEBSOM project. MOVSOM uses a SOM algorithm in combination with a movie relation preserving stretch map algorithm to build a flat landscape of movies.