The paper introduces a counterfactual observability framework for Netflix’s recommender systems, aiming to disentangle raw engagement signals—such as views and clicks—from confounding factors like content quality, model behavior, presentation bias, and audience reach. It proposes three stakeholder‑centered principles and measurement methods that reduce bias, assess relativity, and capture incrementality, applicable to both single‑stage and cascading recommender architectures. The framework is demonstrated through multiple production deployments, showing its effectiveness in enhancing observability across Netflix’s recommendation pipelines.
By Chaoran Guo, Ding Tong, Ting-Po Lee, Scarlet Chen
arXiv:2403. 00802v2 Announce Type: replace-cross Abstract: Production-grade recommender systems rely heavily on a large-scale corpus used by online media services, including Netflix, Pinterest, and Amazon.
By Amit Kumar Jaiswal
arXiv:2608. 10474v1 Announce Type: cross Abstract: Popularity bias in recommendation systems arises when a majority user class generates disproportionate interaction data, causing the system to increasingly favour it while degrading recommendation quality for niche users.
By Sarvesh Shashidhar, Lankireddy Prabhat, Arpit Agarwal, D. Manjunath, Karan Bhukar, Tanmay Khandelwal
arXiv:2412. 20802v3 Announce Type: replace-cross Abstract: Recommender systems are widely used in the digital landscape to match users with content fitting their preferences.
By Aurore Archimbaud, Andreas Alfons, Ines Wilms
FairDiff is a new fairness‑aware diffusion framework designed to mitigate the self‑reinforcing Matthew Effect in Diffusion Recommender Models (DRMs). It introduces Popularity Condition Guidance (PCG) to reweight inference‑time gradients and penalize high‑popularity items, and a Semantic Calibration (SC) module that aligns forward and reverse distributions via optimal transport. Experiments show FairDiff achieves state‑of‑the‑art performance while reducing popularity bias in DRMs.
By Song-Li Wu, Xianquan Wang, Zhaocheng Du, Weinan Gan, Jingyi Wang
SPADE (Serendipitous Pareto Distance Evaluation) is a new metric for recommender systems that simultaneously considers item similarity, popularity, and user relevance. It projects items into a two‑dimensional space and computes a user‑specific Pareto frontier of maximally popular and historically similar items, then averages the minimum Euclidean distance from this frontier for correctly recommended test‑set items. Experiments on five datasets and five baseline algorithms demonstrate that SPADE effectively discourages algorithms from exploiting accuracy‑only metrics and reliably isolates serendipitous discoveries.
By Tobias Vente, Maarten Peirsman, Noah Dani\"els, Hannu Toivonen, Bart Goethals
The study reproduces a prior work on recommender systems that use generated natural‑language user profiles to enhance transparency and user control. It confirms that the User Profile Recommendation (UPR) model performs competitively and that altering these profiles uniformly shifts predicted ratings without changing ranking order. Additional experiments include context ablation, multi‑seed stability, and mechanistic interpretability analysis with the nnsight framework.
This reproducibility study confirms that incorporating generated natural‑language user profiles into recommender systems enhances transparency and allows users to directly intervene by correcting preferences or addressing cold‑start issues. The authors replicated the original findings and extended the evaluation with context ablation, multi‑seed stability tests, and mechanistic interpretability analysis using nnsight. Their results show that while perturbing profiles shifts predicted ratings uniformly across genres, the overall rankings remain unchanged, attributing this to the rating‑regression objective rather than the profile interface.
By Noah Mami\'e, Laurin van den Bergh
arXiv:2606. 04550v1 Announce Type: cross Abstract: E-commerce recommender systems strongly influence which products users consider and purchase, yet sustainability signals such as Product Carbon Footprint (PCF) are almost never available at catalog scale.
By Noah Lund Syrdal, Anders Vestrum, Jorgen Bergh
arXiv:2608. 15780v1 Announce Type: cross Abstract: Stale recommendations are a pervasive challenge and a leading source of user complaints on large-scale content platforms.
By Di Bai, Feng Han, Zhenwei Tang, Jintao Liu, Luoshu Wang, Jialu Liu
arXiv:2607. 14192v1 Announce Type: new Abstract: As recommender systems mature in the past few years, their optimization objectives have evolved from a primary focusing on short-term behavioral signals to a broader emphasis on long-term user engagement and retention.
By Dingsu Wang, Filip Ryzner, Kelly He, Armando Ordorica, David Woo, Aditya Mantha, Liyao Lu, Usha Amrutha Nookala, Haoran Guo, Jiacong He, Olafur Gudmundsson, Matt Chun, Krystal Benitez, Dhruvil Deven Badani, Yijie Dylan Wang
The paper proposes an incremental recommendation system that uses causal modeling to avoid delivering redundant recommendations. By leveraging existing holdback data and a dual‑threshold targeting policy, the authors reduce recommendation impressions by 7% without harming overall content consumption. Joint training with holdback data also improves the calibration of the treated model, suggesting better generalisable representations than purely observational models.
By Athanasios Vlontzos, David Gustafsson, Michael O'Riordan, Ciar\'an M. Gilligan-Lee