Data Science for Next-Generation Recommender Systems

Recommender Systems 2020


Artificial Intelligence





Call for Papers: Special Issue on Data Science for Next-Generation Recommender Systems
We are living in the age of data, where nearly every task we conduct in our daily lives depends on data and can be tracked and supported digitally. Massive data of different types, including numeric variables, images, videos, music, text, etc., could be collected when shopping, working, socializing, communicating, relaxing and traveling, as part of our daily lives. As a multi-disciplinary field that integrates mathematics, statistics and computer science, data science uses scientific methods, processes, algorithms and systems to extract knowledge and insights from structured and unstructured data, with the ultimate goal to support decision making. In this context, recommender systems have been one of the most important applications of data science. Recommender systems use advanced analytics and learning techniques to select relevant and significant information from massive data and inform users’ smart decision-making on their daily needs.
This special issue solicits the latest and significant contributions on developing and applying data science and advanced analytics for building next-generation recommender systems, and particularly on data+model-driven intelligent and personalized recommender systems.
Topics of Interest:
The special issue invites submissions on all topics of data science for recommender systems, including but not limited to:
Advanced data mining, machine learning and deep learning for recommender systems;
Automated recommender systems with automated model selection and parameter tuning in open and dynamic environment;
Big data analytics and its applications to recommender systems;
Context-aware and domain-driven recommender systems;
Data science theories and techniques for recommender systems;
Data-driven behavior modelling, analysis, and prediction for dynamic, session-based, sequential and next-best recommendation;
Non-IID recommender systems with complex couplings, interactions, relations and heterogeneities;
Recommender systems in low-quality large or small data and with misinformation; Personalized recommender systems and precision recommendation;
Recommender systems for light-weighted and energy-efficient devices, IoT, PDA and relevant contexts; and
Surveys, reviews and prospects on data-driven next-generation recommender systems.
Guest Editors:
Yan Wang (yan.wang@mq.edu.au), Macquarie University, Australia
Shoujin Wang (shoujin.wang@mq.edu.au), Macquarie University, Australia
Fikret Sivrikaya (fikret.sivrikaya@gt-arc.com), GT-ARC gGmbH, Berlin, Germany
Sahin Albayrak (sahin.albayrak@dai-labor.de), Technische Universität Berlin, Germany
Important Dates:
Paper submission due: June 30, 2020
First round review notification: August 28, 2020
Further rounds of review may be required based on previous review outcomes
Camera-ready version due: September 30, 2020
Submission Guidelines:
Papers submitted to this special issue for possible publication must be original and must not be under consideration for publication in any other journal or conference. All manuscripts must be prepared according to the journal publication guidelines and author’s instructions which can be found on the website (http://www.springer.com/41060). Papers will be reviewed following the journal standard review process.
Enquiries:
Enquiries about this special issue can be sent to any guest editors.