Welcome to RS_c, the central platform for the RecSys community. We provide curated lists of recommender-systems datasets, algorithms, books, conferences and many resources more. Maybe most importantly, we publish the latest recommender-system news. If you want your news to be reported on RS_c, read here.
HomeCommunity‘Recsperts’ releases its 20th episode; This time on Practical Bandids and Travel Recommendations
‘Recsperts’ releases its 20th episode; This time on Practical Bandids and Travel Recommendations
November 20, 2023
Recsperts is becoming a constant entity in the recommender system community. A few days ago, almost exactly 2 years after its launch, Recspert released its 20th podcast episode. As always, available on Spotify, Apple, Google, Overcast, and Amazon.
In the 20th episode of “Recsperts,” Dr. Bram van den Akker, a Senior Machine Learning Scientist at Booking.com, discusses bandit algorithms and counterfactual learning in decision-making systems, particularly for travel industry recommendations. The conversation covers practical aspects of bandit feedback, challenges in model evaluation and recommendation systems, and nuances of reward signals. The episode ends with a discussion on clickbait in news services. Listeners are encouraged to subscribe and review the podcast.
As a side note, the podcast is, as far as I know, solely created by Marcel Kurovski.
I am the founder of Recommender-Systems.com and head of the Intelligent Systems Group (ISG) at the University of Siegen, Germany https://isg.beel.org. We conduct research in recommender-systems (RecSys), personalization and information retrieval (IR) as well as on automated machine learning (AutoML), meta-learning and algorithm selection. Domains we are particularly interested in include smart places, eHealth, manufacturing (industry 4.0), mobility, visual computing, and digital libraries.
We founded or maintain, among others, LensKit-Auto, Darwin & Goliath, Mr. DLib, and Docear, each with thousand of users; we contributed to TensorFlow, JabRef and others; and we developed the first prototypes of automated recommender systems (AutoSurprise and Auto-CaseRec) and Federated Meta Learning (FMLearn Server and Client).