Recommender systems are a significant assistance in e-commerce/e-business venders to offer valuable data collection for analysis, development and generating recommendations, such as Amazon.com recommendations which offer fruitful products including CDs, DVDs, books, and etc to customers. Recommender systems are the most successful engine to provide a particular user with a set of highest interesting items for personalized suggestions and therefore improve customer relationship management. They do not only suggest interesting items according to user needs and provide personal e-services based on user behaviors. Recommender systems, however, are often facing with the main challenges such as prediction accuracy, scalability, and data sparsity problems. Researchers have tried different ways such as by using optimization and social networks to solve these problems. In the real world, people are connected as a social network. When users want to make a decision, they may consider many objectives earnings an optimal outcome, also affected from relationship among users. Optimization methods are applied in recommendation systems, to deal with a conflict of recommendation objectives, solve data sparsity, and improve prediction accuracy.
This special session aims to provide a forum for researchers to exchange new ideas and knowledge related to recommender systems and applying optimization techniques into item recommendations.
The topics of interest include, but are not limited to:
• Recommender system applications in e-commence, e-business, e-learning and e-government
• New recommender system models and methods
• Social network analysis in recommendation systems
• Tools and techniques for analysing social behaviors
• Centrality measurements in social networks
• Social behaviors learning
• Optimization algorithms and application
• Multi-objective optimization problems in recommendations
|1||Paper Submission Deadline:||Aug 1, 2017|
|2||Notification Acceptance:||Sep 1, 2017|
|3||Camera-ready Paper and Registration:||Sep 25, 2017|