CLiMF Collaborative Less-is-More Filtering, a variant of latent factor CF which optimises a lower bound of the smoothed reciprocal rank of "relevant" items in ranked recommendation lists. The intention is to promote diversity as well as accuracy in the recommendations. The method assumes binary relevance data, as for example in friendship or follow relationships.
CLiMF: Learning to Maximize Reciprocal Rank with Collaborative Less-is-More Filtering Yue Shi, Martha Larson, Alexandros Karatzoglou, Nuria Oliver, Linas Baltrunas, Alan Hanjalic ACM RecSys 2012
To run on the supplied Epinions dataset:
tar xzvf epinions.tar.gz python climf.py --train EP25_UPL5_train.mtx --test EP25_UPL5_test.mtx