OPTIMIZED DEEP COLLABORATIVE FILTERING FOR MOVIE RECOMMENDER SYSTEMS
T. N. Ravi · Journal of Critical Reviews · 2020
Entertainment industry has continuously taken an immense interest in ensuring a personalized experience for each of its viewers in this internet era. Recommender systems are a subclass of systems for filtering information and suggest item especially in streaming services. For finding users with similar products, streaming services such as product recommender systems are important. This paper presents a deep learning approach based on collaborative filtering by incorporating stochastic gradient optimization technique, in order to provide more reliable predictions that can handle cold start and overfitting problems. In user and item based collaborative filtering multiple items are associated for highly identifiable items. Such items are used to train the model of deep learning to predict user ratings on new products and to give final recommendations. The experimental result of the proposed model has been compared with that of the state of art models in terms of Mean Absolute Error and Root Mean Square Error.