时间：2017年11月24日（周五）下午2:00-4:30
地点：博学楼A100
报告人：Iván Palomares Carrascosa
报告人介绍：Iván Palomares Carrascosa is a Lecturer in Computer Science with the School of Computer Science, Electrical and Electronic Engineering, and Engineering Maths (SCEEM), University of Bristol, and visiting Professor with the Management and Economics Sciences School, University of Occidente (Mexico). He received his MSc and PhD degrees (with nationwide distinctions) from the Universities of Granada and Jaén (Spain). Iván’s research interests include AI techniques to support decision making under uncertainty, consensus building, multi-view and collaborative filtering recommender systems, human-machine decision support, fuzzy preference aggregation and data fusion. Applications of his research include management, group recommender systems, disaster management, cybersecurity and energy planning. He has co-authored 13 publications in international journals and over 30 contributions to conferences, along with his recently published co-edited Springer book “Data Analytics and Decision Support for Cybersecurity”.
报告内容：Real-life collective decision making situations typically involve added complexities such as: (I) the need for effectively handling uncertainty due to human vagueness/subjectivity in expressing preferences; (II) the presence of multiple evaluation criteria and participants with diverse background, demanding appropriate preference aggregation methods; and importantly, (III) the importance of making consensual decisions. All the above challenges accentuate in large-group decision making problems involving a large amount of diverse participants, and in group recommender systems, in which an enormous number of items and user preferences must be analysed to recommend the best product or service to a group. Both situations have increasingly become a reality in recent years, due to the rise of social network and crowd-based platforms, along with the latest advances in mobile/cloud computing.
This talk firstly introduces the main challenges of large-group decision making problems, followed by an overview of recent research trends in the topic. Particular focus is given to consensus approaches to support accepted large-group decisions. Secondly, the talk introduces multi-view data approaches in recommender systems, outlining how aggregation techniques can be potentially utilized to intelligently incorporate multiple views of information and improve recommendation processes for groups of users. The talk concludes with a series of “lessons learnt” and future directions of research.
