Research on Understanding the Effect of Deep Learning on User Preferences
- PDF / 2,217,142 Bytes
- 40 Pages / 595.276 x 790.866 pts Page_size
- 40 Downloads / 149 Views
RESEARCH ARTICLE-COMPUTER ENGINEERING AND COMPUTER SCIENCE
Research on Understanding the Effect of Deep Learning on User Preferences Garima Gupta1 · Rahul Katarya1 Received: 25 May 2020 / Accepted: 2 November 2020 © King Fahd University of Petroleum & Minerals 2020
Abstract Recommender systems are becoming more essential than ever as the data available online is increasing manifold. The increasing data presents us with an opportunity to build complex systems that can model the user interactions more accurately and extract sophisticated features to provide recommendations with better accuracy. To construct these complex models, deep learning is emerging as one of the most powerful tools. It can process large amounts of data to learn the structure and patterns that can be exploited. It has been used in recommender systems to solve cold-start problem, better estimate the interaction functions, and extract deep feature representations, among other facets that plague the traditional recommender systems. As big data is becoming more prevalent, there is a need to use tools that can take advantage of such explosive data. An extensive study on recommender systems using deep learning has been performed in the paper. The literature review spans in-depth analysis and comparative study of the research domain. The paper exhibits a vast range of scope for efficient recommender systems in future. Keywords Recommender systems · Machine learning · Deep learning
1 Introduction A recommender system’s goal is to present items to a user, which are most likely to lead to conversion. Conversion might relate to different things in different contexts. For example, for e-commerce, it might mean purchasing the product, and for Netflix, it might mean viewing the content. To achieve this goal, recommender systems have to study the underlying data, consisting of items, users, and their interactions. To study these interactions, we need to extract relevant features and create a system that can learn and model such interactions. Based on the properties of the network that the system exploits, recommender systems can be categorized into content-based, collaborative filtering-based, and hybrid systems. Recommender systems based on content exploit the item’s features to find similar items that the user might
B
Rahul Katarya [email protected] Garima Gupta [email protected]
1
Department of Computer Science and Engineering, Delhi Technological University, Delhi 110042, India
like. A collaborative filtering recommender system uses the user–user interaction. The philosophy being user similar to each other might have similar choices. Systems that combine both these aspects in one or the other way are termed as hybrid systems. Recommender systems use machine learning capabilities at its core to learn the interaction functions and predict items that are most likely to lead to conversion. As the data present online is increasing every day, and the concept of big data is harnessing attention, the dimensionality and modality of data are growing
Data Loading...
