Regularized singular value decomposition in news recommendation system
- Resource Type
- Conference
- Authors
- Ji, Youchun; Hong, Wenxing; Shangguan, Yali; Wang, Huan; Ma, Jing
- Source
- 2016 11th International Conference on Computer Science & Education (ICCSE) Computer Science & Education (ICCSE), 2016 11th International Conference on. :621-626 Aug, 2016
- Subject
- Communication, Networking and Broadcast Technologies
Computing and Processing
General Topics for Engineers
Matrix decomposition
Singular value decomposition
Root mean square
Prediction algorithms
Linear programming
Sparse matrices
Recommender systems
Singular Value Decomposition
11 regularization method
news recommendation system
sparsity
ℓ1 and ℓ2 regularization method
- Language
Singular Value Decomposition was widely used in recommendation system because of the Netflix Prize competition. The method decomposed the user item rating matrix into two matrix with low rank. In order to avoid overfitting the observed user item ratings. It used ℓ2 regularization method to regularize the learned parameters by penalizing their magnitudes. It can solve the problem of sparsity and reduce the dimension of user item rating matrix. It obtain good result using the Root Mean Square Error (RMSE) as evaluation index. But the method cost a lot of time. In this paper, we proposed ℓ1 regularization method and combine ℓ1 and ℓ2 regularization method to regularize the learned parameters of SVD. ℓ1 regularization method show great superiority in the problem of sparsity. Experimental results on XMU News data set and Movie lens data set demonstrate the efficiency and effectiveness of the proposed model. ℓ1 regularization method can represent the users' and items' implicit relation with fewer feature. Combining ℓ1 and ℓ2 regularization method perform well on the RMSE and costing time.