back to list

Project: Diversity of recommendations in collaboration with


Recommender Systems (RSs) have emerged as a way to help users find relevant information as online item catalogs increased in size. There is an increasing interest in systems that produce recommendations that are not only relevant, but also diverse [1]. In addition to users, increased item diversity also benefits the platform and its vendors. Popularity bias in RSs causes popular items to be recommended frequently while the majority of other items are ignored, leading to a long tail problem, where most items are not exposed to users [2]. As users are more likely to interact with items recommended to them, this can create a feedback loop, causing a shift in consumption and homogenization of the user experience [2, 3].

The goal of this project is to develop and evaluate a scalable method to increase diversity of recommender systems across multiple dimensions, while maintaining a reasonable level of relevance. This project is in collaboration with, the largest online retail platform in the Benelux region.


  • A great interest in setting up a sound empirical research design (statistical analysis, A/B testing, etc.).
  • A willingness to get familiar with a real-world recommender system.
  • A basic understanding of recommender systems is preferred.


  1. Neal Lathia, Stephen Hailes, Licia Capra, and Xavier Amatriain. Temporal diversity in recommender systems. In Proceedings of the 33rd International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR ’10, page 210–217, New York, NY, USA,259 2010. Association for Computing Machinery
  2. Allison J. B. Chaney, Brandon M. Stewart, and Barbara E. Engelhardt. How algorithmic confounding in recommendation systems increases homogeneity and decreases utility. In Proceedings of the 12th ACM Conference on Recommender Systems. ACM, sep 2018
  3. Masoud Mansoury, Himan Abdollahpouri, Mykola Pechenizkiy, Bamshad Mobasher, and Robin Burke. Feedback loop and bias amplification in recommender systems. In Proceedings of the 29th ACM International Conference on Information & Knowledge Management, CIKM ’20,267 page 2145–2148, New York, NY, USA, 2020. 
Mykola Pechenizkiy
Secondary supervisor
Hilde Weerts
External location