A Dynamic Collaborative Filtering Algorithm based on Convolutional Neural Networks and Multi-layer Perceptron

In the current information era of enormous amount of data generation, recommendation systems are increasingly used as an efficient way to mitigate information overload in networks. The recommendation systems are used to provide more focused and personalized recommendation of relevant items based on user's historical preferences and constraints. An efficient recommendation system should enrich and improve end user experience. At present, recommendation systems commonly use traditional collaborative filtering algorithms to learn the hidden vectors from the user's commodity behavior matrix. Most of the traditional algorithms characterize data sparseness and cold start problems. Whilst deep learning is being utilized to accurately learn the auxiliary information to enhance the recommendation provided by collaborative filtering techniques, the implementation of deep learning should be fine-tuned in such a way that is satisfies specific application contexts. This paper intends to build a deep collaborative filtering model that integrates Convolutional Neural Networks and Multi-layer Perceptron, addressing the specific requirements of movie recommendation systems. Our proposed model can accurately capture the characteristics of local correlation and explicit and implicit feedback information. In the explicit recommendation task, implicit feedback search is used to embed similar groups, and multi-layer perceptron is used to model user projects, user similar project groups and project similar user groups. Experiments conducted based on the MovieLens dataset for predicting the movie scores demonstrate that our proposed algorithm improves the accuracy of movie score prediction, and outperforms notable traditional collaborative filtering algorithms in terms of alleviating the data sparseness and cold start problems.