Olivier Jeunen

Principal Research Scientist @ Aampe

Google Scholar, ResearchGate, DBLP, Semantic Scholar

Journals and Dagstuhl reports

  1. Evaluation Perspectives of Recommender Systems: Driving Research and Education.
    C. Bauer, A. Said and E. Zangelere. Dagstuhl 24211
    [DOI]

  2. Scheduling on a Budget: Avoiding Stale Recommendations with Timely Updates.
    R. Verachtert, O. Jeunen and B. Goethals. Elsevier MLWA’23
    [DOI]

  3. Pessimistic Decision-Making for Recommender Systems.
    O. Jeunen and B. Goethals. ACM ToRS’22 (Special Issue on Highlights of RecSys ‘21)
    [ACM DL, code]

  4. Embarrassingly Shallow Auto-Encoders for Dynamic Collaborative Filtering.
    O. Jeunen, J. Van Balen and B. Goethals. Springer UMUI’22 (Special Issue on Dynamic Recommender Systems and User Modeling)
    [pdf, code]

Conferences

  1. ∆-OPE: Off-Policy Estimation with Pairs of Policies.
    O. Jeunen and A. Ustimenko. RecSys ’24
    [ACM DL]

  2. Multi-Objective Recommendation via Multivariate Policy Learning.
    O. Jeunen, J. Mandav, I. Potapov, N. Agarwal, S. Vaid, W. Shi and A. Ustimenko. RecSys ’24
    [ACM DL]

  3. Optimal Baseline Corrections for Off-Policy Contextual Bandits.
    S. Gupta, O. Jeunen, H. Oosterhuis and M. de Rijke. RecSys ’24
    [ACM DL]

  4. Powerful A/B-Testing Metrics and Where to Find Them.
    O. Jeunen, S. Baweja, N. Pokharna and A. Ustimenko. RecSys ’24
    [ACM DL]

  5. On (Normalised) Discounted Cumulative Gain as an Off-Policy Evaluation Metric for Top-n Recommendation.
    O. Jeunen, I. Potapov and A. Ustimenko. KDD ‘24.
    [ACM DL]

  6. Learning Metrics that Maximise Power for Accelerated A/B-Tests.
    O. Jeunen and A. Ustimenko. KDD ‘24 (ADS Track).
    [ACM DL]

  7. Monitoring the Evolution of Behavioural Embeddings in Social Media Recommendation.
    S. Saket, O. Jeunen and Md. D. Kalim. SIGIR ‘24 (SIRIP).
    [ACM DL]

  8. Learning-to-Rank with Nested Feedback.
    H. Sagtani, O. Jeunen and A. Ustimenko. ECIR ‘24.
    [arXiv]

  9. Variance Reduction in Ratio Metrics for Efficient Online Experiments.
    S. Baweja, N. Pokharna, A. Ustimenko and O. Jeunen. ECIR ‘24 (Industry Track).
    [arXiv]

  10. Ad-load Balancing via Off-policy Learning in a Content Marketplace.
    H. Sagtani, M. Jhawar, R. Mehrotra and O. Jeunen. WSDM ‘24.
    [ACM DL, arXiv, video]

  11. On Gradient Boosted Decision Trees and Neural Rankers: A Case-Study on Short-Video Recommendations at ShareChat.
    O. Jeunen, H. Sagtani, H. Doi, R. Karimov, N. Pokharna, D. Kalim, A. Ustimenko, C. Green, R. Mehrotra and W. Shi. FIRE’23.
    [arXiv]

  12. A Probabilistic Position Bias Model for Short-Video Recommendation Feeds.
    O. Jeunen. RecSys’23.
    [ACM DL, arXiv, code]

  13. Off-Policy Learning-to-Bid with AuctionGym.
    O. Jeunen, S. Murphy and B. Allison. KDD’23 (ADS Track).
    [ACM DL, AuctionGym]

  14. Disentangling Causal Effects from Sets of Interventions in the Presence of Unobserved Confounders.
    O. Jeunen, C. M. Gilligan-Lee, R. Mehrotra and M. Lalmas. NeurIPS’22.
    [NeurIPS, arXiv, code, video]

  15. Pessimistic Reward Models for Off-Policy Learning in Recommendation.
    O. Jeunen and B. Goethals. RecSys’21 (Best Student Paper Award)
    [ACM DL, pdf, code]

  16. Top-K Contextual Bandits with Equity of Exposure.
    O. Jeunen and B. Goethals. RecSys’21
    [ACM DL, pdf, code]

  17. Closed-Form Models for Collaborative Filtering with Side-Information.
    O. Jeunen, J. Van Balen and B. Goethals. RecSys’20 (Late-Breaking-Result)
    [ACM DL, pdf, code]

  18. Joint Policy-Value Learning for Recommendation.
    O. Jeunen, D. Rohde, F. Vasile and M. Bompaire. KDD’20
    [ACM DL, pdf, code]

  19. Efficient Similarity Computation for Collaborative Filtering in Dynamic Environments.
    O. Jeunen, K. Verstrepen and B. Goethals. RecSys’19
    [ACM DL, pdf, code]

  20. Revisiting Offline Evaluation for Implicit-Feedback Recommender Systems.
    O. Jeunen. RecSys’19 (Doctoral Symposium)
    [ACM DL, pdf]

  21. A Machine Learning Approach for IEEE 802.11 Channel Allocation.
    O. Jeunen, P. Bosch, M. Van Herwegen, K. Van Doorselaer, N. Godman and S. Latré. CNSM’18
    [pdf]

Workshops, Tutorials, Demos & Others

  1. A Simple Model to estimate Sharing Effects in Social Networks.
    O. Jeunen. CONSEQUENCES ‘24 (RecSys Workshop).
    [arXiv, code]

  2. CONSEQUENCES — 3nd Workshop on Causality, Counterfactuals and Sequential Decision-Making for Recommender Systems.
    O. Jeunen, H. Oosterhuis, Y. Saito, F. Vasile and Y. Wang. CONSEQUENCES ‘24 (RecSys Workshop).
    [webpage]

  3. RecFusion: A Binomial Diffusion Process for 1D Data for Recommendation.
    G. Bénédict, O. Jeunen, S. Papa, S. Barghav, D. Odijk and M. de Rijke. GenRec ‘23 (CIKM Workshop).
    [arXiv]

  4. Offline Recommender System Evaluation under Unobserved Confounding.
    O. Jeunen and B. London. CONSEQUENCES ‘23 (RecSys Workshop).
    [arXiv, code, video]

  5. Ad-load Balancing via Off-policy Learning in a Content Marketplace.
    H. Sagtani, M. Jhawar, R. Mehrotra and O. Jeunen. CONSEQUENCES ‘23 (RecSys Workshop).
    [arXiv, video]

  6. A Common Misassumption in Online Experiments with Machine Learning Models.
    O. Jeunen. SIGIR Forum, PERSPECTIVES ‘23 (RecSys Workshop).
    [arXiv, code, video]

  7. CONSEQUENCES — 2nd Workshop on Causality, Counterfactuals and Sequential Decision-Making for Recommender Systems.
    O. Jeunen, T. Joachims, H. Oosterhuis, Y. Saito, F. Vasile and Y. Wang. CONSEQUENCES ‘23 (RecSys Workshop).
    [webpage]

  8. A Probabilistic Position Bias Model for Short-Video Recommendation Feeds.
    O. Jeunen. ML4SM ‘23 (The WebConf Workshop).
    [video]

  9. Practical Bandits: An Industry Perspective.
    B. van den Akker, O. Jeunen, Y. Li, B. London, Z. Nazari and D. Parekh. The WebConf’23, WSDM ‘24 (Tutorial)
    [recording, webpage, arXiv]

  10. A Probabilistic Framework to Learn Auction Mechanisms via Gradient Descent.
    O. Jeunen, L. Stavrogiannis, A. Sayedi and B. Allison. AI4WebAds’23 (AAAI Workshop)
    [pdf, video]

  11. CONSEQUENCES — Causality, Counterfactuals and Sequential Decision-Making for Recommender Systems.
    O. Jeunen, T. Joachims, H. Oosterhuis, Y. Saito and F. Vasile. CONSEQUENCES ‘22 (RecSys Workshop).
    [ACM DL, webpage]

  12. Learning to Bid with AuctionGym.
    O. Jeunen, S. Murphy and B. Allison. AdKDD ‘22 (KDD Workshop, Best Paper Award).
    [pdf, code, video]

  13. Disentangling Causal Effects from Sets of Interventions in the Presence of Unobserved Confounders.
    O. Jeunen, C. M. Gilligan-Lee, R. Mehrotra and M. Lalmas. WHY’21 (NeurIPS Workshop)
    [pdf]

  14. Offline Evaluation of Reward-Optimizing Recommender Systems: The Case of Simulation. I. Aouali, A. Benhalloum, M. Bompaire, B. Heymann, O. Jeunen, D. Rohde, O. Sakhi and F. Vasile. SimuRec ‘21 (Recsys Workshop)
    [arXiv]

  15. Recommender Systems through the Lens of Decision Theory:
    Unifying Policy- and Vaue-based Aproaches to Recommendation.
    F. Vasile, D. Rohde, O. Jeunen, A. Benhalloum and O. Sakhi. WWW’21 (Tutorial)
    [ACM DL, webpage]

  16. An Empirical Evaluation of Doubly Robust Learning for Recommendation.
    O. Jeunen and B. Goethals. REVEAL’20 (RecSys Workshop)
    [pdf]

  17. A Gentle Introduction to Recommendation as Counterfactual Policy Learning.
    F. Vasile, D. Rohde, O.Jeunen and A. Benhalloum. UMAP’20 (Tutorial)
    [ACM DL, pdf, slides & notebooks, video]

  18. Three Methods for Training on Bandit Feedback.
    D. Mykhaylov, D. Rohde, F. Vasile, M. Bompaire and O. Jeunen. CausalML’19 (NeurIPS Workshop)
    [arXiv]

  19. Learning from Bandit Feedback: An Overview of the State-of-the-art.
    O. Jeunen, D. Mykhaylov, D. Rohde, F. Vasile, A. Gilotte and M. Bompaire. REVEAL’19 (RecSys Workshop)
    [arXiv]

  20. On the Value of Bandit Feedback for Offline Recommender System Evaluation.
    O. Jeunen, D. Rohde and F. Vasile. REVEAL’19 (RecSys Workshop)
    [arXiv, notebook]

  21. Interactive Evaluation of Recommender Systems with SNIPER - An Episode Mining Approach.
    S. Moens, O. Jeunen and B. Goethals. RecSys’19 (Demo)
    [ACM DL, pdf, code, video]

  22. Predicting Sequential User Behaviour with Session-based Recurrent Neural Networks.
    O. Jeunen and B. Goethals. WSDM Cup’19 (WSDM Workshop)
    [pdf, code]

  23. Fair Offline Evaluation Methodologies for Implicit-Feedback Recommender Systems with MNAR Data.
    O. Jeunen, K. Verstrepen and B. Goethals. REVEAL’18 (RecSys Workshop)
    [pdf]

Theses

  1. Offline Approaches to Recommendation with Online Success.
    PhD in Computer Science, 2021.
    [pdf]

  2. Data-Driven Frequency Planning in IEEE 802.11 Networks.
    MSc in Computer Science, 2017.