Deep learning techniques for rating prediction: a survey of the state-of-the-art

Abstract

With the growth of online information, varying personalization drifts and volatile behaviors of internet users, recommender systems are effective tools for information filtering to overcome the information overload problem. Recommender systems utilize rating prediction approaches i.e. predicting the rating that a user will give to a particular item, to generate ranked lists of items according to the preferences of each user in order to make personalized recommendations. Although previous recommendation systems are effective in creating attired recommendations, however, they still suffer from different types of challenges such as accuracy, scalability, cold-start, and data sparsity. In the last few years, deep learning has attained substantial interest in various research areas such as computer vision, speech recognition, and natural language processing. Deep learning based approaches are vigorous in not only performance improvement but also to feature representations learning from the scratch. The impact of deep learning is also prevalent, recently validating its efficacy on information retrieval and recommender systems research. In this study, a comprehensive review of deep learning-based rating prediction approaches is provided to help out new researchers interested in the subject. More concretely, the classification of deep learning-based recommendation/rating prediction models is provided and articulated along with an extensive summary of the state-of-the-art. Lastly, new trends are exposited with new perspectives pertaining to this novel and exciting development of the field.

A Survey of Human-in-the-loop for Machine Learning

“…At present, deep learning has played an irreplaceable role in many fields [1,2]. The great success of deep learning is due to larger-scale models [5].…”

“…However, most parsing technologies still face several challenges: (1) the purpose or expression of users can be ambiguous or vague under some circumstances, posing obstacles for them to get the ground truth in one shot, (2) in the real-world scenario, the performance of state-of-the-art parsers are generally not high enough, and (3) since the mainstream neural network-based models are known as "black-box", which indicates the lack of explainability, it is difficult for end-users to verify the parsing results independently. Currently, Yao et al [83] propose to allow semantic parsers system to ask end-users clarification Input Layer Hidden Layers Output Layer a [4] X Ŷ a [1] 1 a [1] 2 a [1] 3 a [1] n a [2] 1 a [2] 2 a [2] 3 a [2] n a [3] 1 a [3] 2 a [3] 3 a [3] n questions and produce an If-Then program at the same time. Su et al [84] have proven that end-users particularly preferred a parser system based on an interactive manner over the noninteractive counterpart for NLP interfaces to web APIs.…”

“…Deep learning is a frontier for artificial intelligence, aiming to be closer to its primary goal -artificial intelligence. Deep learning has seen great success in a wide variety of applications, such as natural language processing, speech recognition, medical applications, computer vision, and intelligent transportation system [1,2,3,4]. The great success of deep learning is due to the larger models [5].…”

TTRS: Tinkoff Transactions Recommender System benchmark

“…In this work, we are focused on the former task. Other similar tasks, for example, click-through rate prediction [20], rating prediction [23], are not the focus of our work.…”

“…In the current era of big data and global personalization, Recommender Systems (RecSys) are playing a pivotal role in improving user experience in a large variety of domains: movies [43], music [35], news [12] and many more [5,34,55]. There are many different types of recommendations, such as rating prediction [23], as well as top-n [9], sequential [54], session-based [53], and next-basket Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored.…”