S. Lai, Y.
Liu, H. Gu, L. Xu, K. Liu, S. Xiang, J. Zhao, R. Diao, L. Xiang, H. Li & D.
Wang; JMLR W&CP 18:137–151, 2012.
Hybrid Recommendation Models for Binary User Preference Prediction Problem
This paper presents detailed information of our solutions to the task 2 of KDD Cup
2011. The task 2 is called binary user preference prediction problem in the paper because it aims
at separating tracks rated highly by speciﬁc users from tracks not rated by them, and the
solutions of this task can be easily applied to binary user behavior data. In the contest, we
ﬁrstly implemented many diﬀerent models, including neighborhood-based models, latent
factor models, content-based models, etc. Then, linear combination is used to combine
diﬀerent models together. Finally, we used robust post-processing to further reﬁne the
special user-item pairs. The ﬁnal error rate is 2.4808% which placed number 2 in the
Page last modified on Tue May 29 10:23:19 2012.