We have developed a toolset to help teams to design for serendipity. The tool is almost ready to show itself to the world.
Leave your email address here and we’ll notify you when the tool is available.
RecPack is a Python toolkit that helps researchers and data scientists easily build, test, and compare recommendation systems using ready-to-use datasets, methods, and evaluation tools. It is designed to be easy to work with, reliable, and reproducible, using sensible defaults and a familiar workflow inspired by popular data science tools. You can find more information at https://recpack.froomle.ai/
Demo presented at the Imec Technology Forum (ITF) 2024:
Demo presented at Trefdag Digitaal Vlaanderen:
Binst, B. (Creator), Michiels, L. (Creator), Smets, A. (Creator) (7 May 2025). Interview transcripts: Brett Binst, Lien Michiels, and Annelien Smets (2025). What Is Serendipity? An Interview Study to Conceptualize Experienced Serendipity in Recommender Systems. In Proceedings of the 33rd ACM Conference on User Modeling, Adaptation and Personalization (UMAP '25). Zenodo. https://zenodo.org/records/15131547
The Serendipity Society (SerSoc) is comprised of researchers, practitioners and the serendipity-curious, examining the complex phenomenon of serendipity from a variety of disciplinary and organizational perspectives. Given the growing interest among business and industry, public and academic institutions in developing spaces for serendipity, our mission is to create and nurture an active network of serendipity researchers and practitioners, which
supports collaboration among senior and junior scholars,
promotes rigorous and interdisciplinary research,
works toward the consolidation of practice and the development of theory,
creates a platform from which to develop serendipity research as an independent field of study,
provides a resource of expertise on serendipity to which organizations, funders, innovators, and planners can turn.
The Serendipity Society is chaired by Samantha Copeland .
Annelien Smets is Chair of the Serendipity Academic Researchers Network (SARN), part of SerSoc.
NORMalize sets out to provide a platform for researchers and practitioners from different domains to discuss challenges related to the normative design and evaluation of recommender systems.
Recommender systems are used in many different domains, from recommending recipes to song playlists. They increasingly act as "gatekeepers" to what users are exposed to online. Therefore it is important that we, as designers of these systems, think about the norms and values appropriate to the domain when designing and evaluating these recommender systems, such that they have a positive impact on society.
Should recipe recommenders prioritize healthy choices over not so healthy choices? Or should they prioritize sustainability and recommend recipes that make use of local, fresh ingredients? Or maybe we need both?
Should news recommenders provide sufficiently diverse recommendations? Should we strive to expose users to content that contradicts their political beliefs?
How can we operationalize these norms and values in recommender systems?
How can we design normative recommender systems?
How can we evaluate recommender systems according to our norms and values?
At NORMalize, we aim to provide some preliminary answers to the above questions, and many more through guided discussions that bring together industry and academia and scholars from different research domains.
NORMalize is co-organized by Lien Michiels.