How Much of Your Journalism Goes Unseen?
The mission of modern digital publishing is no longer just creating journalism. It is ensuring every piece of journalism finds the audience that values it most.
Read NoteFroomle Notes
Insights, Ideas andTechnical Deep Dives
Exploring the intersection of advanced AI, recommender systems, and high-impact media journalism.
Collaborative Filtering for News Recommendations
Why reader behaviour is often a stronger signal than article text when recommending news.
Build vs Buy: Choosing Personalization Software
How publishers can evaluate whether to build personalization technology in-house, buy a specialist solution, or rely on a broader vendor suite.
Avoiding the Filter Bubble
How AI personalization can increase content diversity, not just popularity.
The Battle for Audience Attention in News Media
In a landscape where giants like Google and Meta have conditioned audiences to expect personalization, offering tailored experiences is no longer a luxury but a strategic necessity.
What Does “Popular” Really Mean?
Why even the simplest ranking metric is more subtle and dynamic than it seems.
Scientific Excellence
Rooted in Research
Every Froomle module is backed by published academic research in recommender systems and personalization.
Recommender Systems Publications
Unifying Nearest Neighbors Collaborative Filtering
Proceedings of the 8th ACM Conference on Recommender Systems, 177-184
Pessimistic reward models for off-policy learning in recommendation
Proceedings of the 15th ACM Conference on Recommender Systems, 63-74
Top-n recommendation for shared accounts
Proceedings of the 9th ACM Conference on Recommender Systems, 59-66
Collaborative Filtering for Binary, Positiveonly Data
ACM SIGKDD Explorations Newsletter 19 (1), 1-21
Recpack: An (other) experimentation toolkit for top-n recommendation using implicit feedback data
Proceedings of the 16th ACM Conference on Recommender Systems, 648-651
Fair Offline Evaluation Methodologies for Implicit-Feedback Recommender Systems with MNAR Data
The 1st International Workshop on Offline Evaluation for Recommender Systems...
Closed-form models for collaborative filtering with side-information
Proceedings of the 14th ACM Conference on Recommender Systems, 651-656
Pessimistic decision-making for recommender systems
ACM Transactions on Recommender Systems 1 (1), 1-27
Are we forgetting something? Correctly evaluate a recommender system with an optimal training window
PERSPECTIVES 2022: Proceedings of the Perspectives on the Evaluation of...
Efficient similarity computation for collaborative filtering in dynamic environments
Proceedings of the 13th ACM Conference on Recommender Systems, 251-259
High-dimensional sparse embeddings for collaborative filtering
Proceedings of the Web Conference 2021, 575-581
An empirical evaluation of doubly robust learning for recommendation
Proceedings of the REVEAL Workshop on Bandit and Reinforcement Learning from...
Embarrassingly shallow auto-encoders for dynamic collaborative filtering
User Modeling and User-Adapted Interaction 32 (4), 509-541
A framework and toolkit for testing the correctness of recommendation algorithms
ACM Transactions on Recommender Systems 2 (1), 1-45
Interactive evaluation of recommender systems with SNIPER: an episode mining approach
Proceedings of the 13th ACM Conference on Recommender Systems, 538-539
On-the-Fly News Recommendation Using Sequential Patterns.
INRA@ RecSys, 29-34
Predicting sequential user behaviour with session-based recurrent neural networks: our approach to the 2019 WSDM Cup Sequential Skip Prediction Challenge
Proceedings of the 2019 WSDM Cup Workshop, February 15th 2019, Melbourne...
Leveraging sequential episode mining for session-based news recommendation
International Conference on Web Information Systems Engineering, 594-608
The impact of a popularity punishing hyperparameter on ItemKNN recommendation performance
European Conference on Information Retrieval, 646-654
Scheduling on a budget: Avoiding stale recommendations with timely updates
Machine Learning with Applications 11, 100455
Modelling users with item metadata for explainable and interactive recommendation
arXiv preprint arXiv:2207.00350
Session-based News Recommendation Using Cohesive Patterns
2024 IEEE International Conference on Big Data (BigData), 440-447
A Neighbourhood-based Location-and Time-aware Recommender System.
ORSUM@ RecSys
GaMuSo: graph base music recommendation in a social bookmarking service
International Symposium on Intelligent Data Analysis, 138-149
Weighted Tensor Decompositions for Context-aware Collaborative Filtering
arXiv preprint arXiv:2503.08393
Non-Stationary Multi-Armed Bandits for News Recommendations
Working paper
What Data is Really Necessary? A Feasibility Study of Inference Data Minimization for Recommender Systems
Proceedings of the 34th ACM International Conference on Information and...
Scalable Evaluation of Rule-Based Recommender Systems: Algorithms and Benchmarks
Rules and Reasoning: 9th International Joint Conference, RuleML+ RR 2025...
Neighborhood-Based Collaborative Filtering Bandits
Challenges and Algorithms for Knowledge Discovery from Data: Essays...
4.5 Evaluating the Long-Term Impact of Recommender Systems
Evaluation Perspectives of Recommender Systems: Driving Research and...