Search

In recent years, the ever-growing contents (movies, clothes, books, etc.) accessible and buyable via the Internet have led to the information overload issue and therefore the item targeting problem. Indeed, the huge mass of contents complexifies the identification of items fitting users' expectations. As powerful filtering tools, recommender systems efficiently alleviate the item targeting issue. Collaborative filtering-based methods are among the most influential algorithms adopted in recommender systems. Among collaborative filtering-based methods, model-based approaches are widely used in recent powerful recommendation methods. Due to its efficiency, the matrix factorization technique is spreadly employed in model-based approaches. However, those methods badly deal with issues such as data sparseness and cold-start problems that severely affect the recommendation quality. To overcome these limitations shown by state-of-the-art methods, we propose in this paper a recommender approach that couples the effectiveness of an enhanced matrix factorization technique to the power of a deep neural network model. In the first step, the user's latent factors and item latent factors are extracted from a doubly-regularized matrix factorization process. Thereafter, those latent factors are used to feed a deep learning structure in a forward-propagation process, and a normalized cross-entropy method is used to increase the precision of the deep neural network through a backpropagation process. The end prediction is made by combining results from the matrix factorization step and the deep neural structure. Extensive experiments are conducted on real-world datasets and show that our proposal outperforms other methods in terms of prediction accuracy and recommendation quality. [ABSTRACT FROM AUTHOR]

As an important technology of Internet products, the recommender system can help users to obtain the information they need and alleviate the problem of information overload. In the implicit feedback recommender system, the key issue is how to represent users and products. In recent years, deep learning has achieved good performance in many fields including speech recognition, computer vision and natural language processing. We propose a deep learning-enhanced framework for implicit feedback recommendation. In this framework, we simultaneously learn the new distributed representation of users and items via node2vec to improve the negative sampling strategy. Finally, we develop a deep neural network recommendation model to integrate user features, product features and interaction features. Experiments conducted on two real-world datasets demonstrate the effectiveness of the proposed framework and methods. [ABSTRACT FROM AUTHOR]

In the field of artificial intelligence, the development of many technologies requires technical support for relational classification. Recently, deep learning has been applied more and more to text-based entity relationship classification tasks, but most of the previous methods need to use syntax or dependency structure feature. However, due to the time and space complexity of syntactic parsing, the structural features are inconvenient to use directly in the pre-processing stage. In addition, structural features may have serious domain dependence problems. This paper studies the current recommendation algorithm, analyzes the current research status of the recommendation system, and deeply analyzes the research of deep learning in the field of recommendation systems, based on BPSO algorithm, the context complex segmentation method is applied, and then the deep convolutional neural network is applied for feature extraction. The extracted feature set is sent to WordEmbedding, and using the technology to generates the word vector, the input layer of the CBOW is used to represent the size of the training window. The experimental results show that the model has obvious advantages over the methods proposed in other literature. It can adapt to multi-category context semantic analysis, more accurate related recommendations, and obtain a better user experience. [ABSTRACT FROM AUTHOR]