Boosting collaborative filtering with an ensemble of co-trained recommenders.
Arthur F. Da CostaMarcelo G. ManzatoRicardo J. G. B. CampelloPublished in: Expert Syst. Appl. (2019)
Keyphrases
- collaborative filtering
- negative correlation learning
- ensemble learning
- ensemble methods
- recommender systems
- weak learners
- base classifiers
- training set
- artificial neural networks
- ensemble classification
- matrix factorization
- weak classifiers
- decision stumps
- ensemble classifier
- randomized trees
- random forest
- majority voting
- base learners
- neural network
- decision trees
- personalized recommendation
- data sparsity
- recommendation systems
- learning algorithm
- random forests
- generalization ability
- user profiles
- feature selection
- weighted voting
- boosting algorithms
- prediction accuracy
- decision tree ensembles
- product recommendation
- cold start
- user preferences
- user ratings
- transfer learning
- adaboost algorithm
- implicit feedback
- machine learning methods
- user interests
- benchmark datasets
- training process
- recommendation algorithms
- accurate classifiers
- content based filtering
- multilayer perceptron
- regression problems
- multi class
- training data
- generalization error