{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,2]],"date-time":"2025-08-02T19:10:51Z","timestamp":1754161851810,"version":"3.41.2"},"reference-count":83,"publisher":"Association for Computing Machinery (ACM)","issue":"1","funder":[{"name":"PICAE","award":["2021SGR01104 (Generalitat de Catalunya) and grant PID2022-136436NB-I00 funded by MICIU\/AEI\/10.13039\/501100011033"],"award-info":[{"award-number":["2021SGR01104 (Generalitat de Catalunya) and grant PID2022-136436NB-I00 funded by MICIU\/AEI\/10.13039\/501100011033"]}]},{"name":"Horizon Europe Programme under the AI4Debunk Project","award":["101135757"],"award-info":[{"award-number":["101135757"]}]},{"name":"SAFEXPLAIN","award":["101069595"],"award-info":[{"award-number":["101069595"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Recomm. Syst."],"published-print":{"date-parts":[[2026,3,31]]},"abstract":"<jats:p>Part of the success of an online media platform depends on its ability to convert first-time users into recurring ones. However, this task is often challenging due to the Pure Cold-start problem, which refers to the difficulty of providing useful recommendations to users without historical data. Although presenting a list of popular items may seem like an easy fix, it can lead to the \u201dpopularity bias\u201d problem.<\/jats:p>\n          <jats:p>In this article, we address a specific issue: the Contextual Pure Cold-start Problem in Public Service Media (PSM) scenarios, characterized by the absence of user-specific data and the presence of only anonymous and limited contextual information. We propose a novel approach aligned with PSM values in recommendations, as ensuring these values is crucial for their task. Our approach seeks to enhance the equity of recommendation rankings by incorporating various types of uncertainty, providing a solution that ensures a fairer exposure to items and broader coverage of the PSM catalog. Using a substantial dataset of real interactions from a public television network, our approach successfully mitigates the \u201dpopularity bias\u201d issue through the use of an uncertainty-based stochastic ranker. Consequently, we achieve a 64% improvement in fair exposure and a 42% increase in coverage metrics, with only an 8% reduction in Hit Rate accuracy metrics.<\/jats:p>","DOI":"10.1145\/3729245","type":"journal-article","created":{"date-parts":[[2025,4,10]],"date-time":"2025-04-10T07:19:06Z","timestamp":1744269546000},"page":"1-27","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Solving the Contextual Pure Cold-Start Problem under Uncertainty"],"prefix":"10.1145","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3384-1423","authenticated-orcid":false,"given":"Paula G\u00f3mez","family":"Duran","sequence":"first","affiliation":[{"name":"University of Barcelona","place":["Barcelona, Spain"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8103-391X","authenticated-orcid":false,"given":"Axel","family":"Brando","sequence":"additional","affiliation":[{"name":"Barcelona Supercomputing Center","place":["Barcelona, Spain"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1484-539X","authenticated-orcid":false,"given":"Jordi","family":"Vitri\u00e0","sequence":"additional","affiliation":[{"name":"University of Barcelona","place":["Barcelona, Spain"]}]}],"member":"320","published-online":{"date-parts":[[2025,7,29]]},"reference":[{"key":"e_1_3_2_2_2","first-page":"413","article-title":"Managing popularity bias in recommender systems with personalized re-ranking","author":"Abdollahpouri Himan","year":"2019","unstructured":"Himan Abdollahpouri, Robin Burke, and Bamshad Mobasher. 2019. Managing popularity bias in recommender systems with personalized re-ranking. In Proceedings of the 32nd International Florida Artificial Intelligence Research Society Conference (FLAIRS\u201919), 413\u2013418. arxiv:1901.07555https:\/\/www.aaai.org\/ocs\/index.php\/FLAIRS\/FLAIRS19\/paper\/viewPaper\/18199","journal-title":"Proceedings of the 32nd International Florida Artificial Intelligence Research Society Conference (FLAIRS\u201919)"},{"key":"e_1_3_2_3_2","series-title":"CEUR Workshop Proceedings","volume-title":"RMSE@RecSys","volume":"2440","author":"Abdollahpouri Himan","year":"2019","unstructured":"Himan Abdollahpouri, Masoud Mansoury, Robin Burke, and Bamshad Mobasher. 2019. The unfairness of popularity bias in recommendation. In RMSE@RecSys(CEUR Workshop Proceedings, Vol. 2440). CEUR-WS.org. http:\/\/dblp.uni-trier.de\/db\/conf\/recsys\/rmse2019.html#AbdollahpouriMB19"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.entcom.2021.100418"},{"key":"e_1_3_2_5_2","first-page":"175","volume-title":"Conformal and Probabilistic Prediction with Applications","author":"Angelopoulos Anastasios N.","year":"2023","unstructured":"Anastasios N. Angelopoulos, Karl Krauth, Stephen Bates, Yixin Wang, and Michael I. Jordan. 2023. Recommendation systems with distribution-free reliability guarantees. In Conformal and Probabilistic Prediction with Applications. PMLR, 175\u2013193."},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098173"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657900"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.tate.2022.103985"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10791-017-9312-z"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.14763\/2016.1.401"},{"key":"e_1_3_2_11_2","volume-title":"Aleatoric Uncertainty Modelling in Regression Problems Using Deep Learning","author":"Brando Axel","year":"2022","unstructured":"Axel Brando. 2022. Aleatoric Uncertainty Modelling in Regression Problems Using Deep Learning. PhD dissertation. Universitat de Barcelona."},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/3336191.3371844"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jenvman.2015.02.010"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2018.03.004"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/1722149.1722154"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/3564284"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-020-01835-9"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/1864708.1864721"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3411962"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467089"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3096609"},{"key":"e_1_3_2_22_2","volume-title":"Probabilistic Deep Learning: With Python, Keras and TensorFlow Probability","author":"D\u00fcrr O.","year":"2020","unstructured":"O. D\u00fcrr, B. Sick, and E. Murina. 2020. Probabilistic Deep Learning: With Python, Keras and TensorFlow Probability. Manning Publications."},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2021.102655"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512077"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/CCAA.2017.8229786"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/3523227.3547380"},{"key":"e_1_3_2_27_2","unstructured":"Ruocheng Guo Jean-Fran\u00e7ois Ton Yang Liu and Hang Li. 2024. Inference-time Stochastic Ranking with Risk Control. arxiv:2306.07188 [cs.LG] https:\/\/arxiv.org\/abs\/2306.07188"},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3615011"},{"key":"e_1_3_2_29_2","article-title":"Maximum likelihood estimation of Dirichlet distribution parameters","volume":"18","author":"Huang Jonathan","year":"2005","unstructured":"Jonathan Huang. 2005. Maximum likelihood estimation of Dirichlet distribution parameters. CMU Technique Report 18 (2005).","journal-title":"CMU Technique Report"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3157042"},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-021-05946-3"},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/3427423.3427425"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.3389\/fdata.2023.1157899"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/3460231.3474248"},{"key":"e_1_3_2_35_2","article-title":"What uncertainties do we need in Bayesian deep learning for computer vision?","volume":"30","author":"Kendall Alex","year":"2017","unstructured":"Alex Kendall and Yarin Gal. 2017. What uncertainties do we need in Bayesian deep learning for computer vision? Advances in Neural Information Processing Systems 30 (2017).","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_36_2","first-page":"3499","volume-title":"International Conference on Machine Learning","author":"Kool Wouter","year":"2019","unstructured":"Wouter Kool, Herke Van Hoof, and Max Welling. 2019. Stochastic beams and where to find them: The Gumbel-top-k trick for sampling sequences without replacement. In International Conference on Machine Learning. PMLR, 3499\u20133508."},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2016.08.014"},{"key":"e_1_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.3390\/info10040150"},{"key":"e_1_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2944214"},{"key":"e_1_3_2_40_2","article-title":"Simple and scalable predictive uncertainty estimation using deep ensembles","volume":"30","author":"Lakshminarayanan Balaji","year":"2017","unstructured":"Balaji Lakshminarayanan, Alexander Pritzel, and Charles Blundell. 2017. Simple and scalable predictive uncertainty estimation using deep ensembles. Advances in Neural Information Processing Systems 30 (2017).","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.2018.3093"},{"key":"e_1_3_2_42_2","article-title":"Toprank: A practical algorithm for online stochastic ranking","volume":"31","author":"Lattimore Tor","year":"2018","unstructured":"Tor Lattimore, Branislav Kveton, Shuai Li, and Csaba Szepesvari. 2018. Toprank: A practical algorithm for online stochastic ranking. Advances in Neural Information Processing Systems 31 (2018).","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2013.09.005"},{"key":"e_1_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2022.103738"},{"key":"e_1_3_2_45_2","article-title":"Responsible AI at the BBC: Our Machine Learning Engine Principles","author":"Macgregor Myrna","year":"2021","unstructured":"Myrna Macgregor. 2021. Responsible AI at the BBC: Our Machine Learning Engine Principles. https:\/\/www.bbc.co.uk\/rd\/publications\/responsible-ai-at-the-bbc-our-machine-learning-engine-principles","journal-title":"https:\/\/www.bbc.co.uk\/rd\/publications\/responsible-ai-at-the-bbc-our-machine-learning-engine-principles"},{"key":"e_1_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1145\/3477140"},{"key":"e_1_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1126\/science.159.3810.56"},{"key":"e_1_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00146-020-00950-y"},{"key":"e_1_3_2_49_2","article-title":"Multi-gradient descent for multi-objective recommender systems","author":"Milojkovic Nikola","year":"2019","unstructured":"Nikola Milojkovic, Diego Antognini, Giancarlo Bergamin, Boi Faltings, and Claudiu Musat. 2019. Multi-gradient descent for multi-objective recommender systems. arXiv preprint arXiv:2001.00846 (2019).","journal-title":"arXiv preprint arXiv:2001.00846"},{"key":"e_1_3_2_50_2","article-title":"Estimating a Dirichlet Distribution","author":"Minka Thomas","year":"2000","unstructured":"Thomas Minka. 2000. Estimating a Dirichlet Distribution. https:\/\/vismod.media.mit.edu\/pub\/tpminka\/papers\/minka-dirichlet.ps.gz","journal-title":"https:\/\/vismod.media.mit.edu\/pub\/tpminka\/papers\/minka-dirichlet.ps.gz"},{"key":"e_1_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.1002\/9781119995784"},{"key":"e_1_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462830"},{"key":"e_1_3_2_53_2","doi-asserted-by":"publisher","DOI":"10.1145\/2959100.2959136"},{"key":"e_1_3_2_54_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10844-022-00698-5"},{"key":"e_1_3_2_55_2","doi-asserted-by":"publisher","DOI":"10.1145\/1454008.1454012"},{"key":"e_1_3_2_56_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11192-020-03766-1"},{"issue":"9","key":"e_1_3_2_57_2","first-page":"22","article-title":"Non-personalized recommender systems and user-based collaborative recommender systems","volume":"6","author":"Poriya Anil","year":"2014","unstructured":"Anil Poriya, Tanvi Bhagat, Neev Patel, and Rekha Sharma. 2014. Non-personalized recommender systems and user-based collaborative recommender systems. International Journal of Applied Information Systems 6, 9 (2014), 22\u201327.","journal-title":"International Journal of Applied Information Systems"},{"key":"e_1_3_2_58_2","article-title":"How Instagram and Facebook are intentionally designed to mimic addictive painkillers","volume":"25","author":"Schw\u00e4r H.","year":"2021","unstructured":"H. Schw\u00e4r. 2021. How Instagram and Facebook are intentionally designed to mimic addictive painkillers. Business Insider. Retrieved October 25, 2021.","journal-title":"Business Insider."},{"key":"e_1_3_2_59_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.116478"},{"key":"e_1_3_2_60_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-019-01477-6"},{"key":"e_1_3_2_61_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2022.12.030"},{"key":"e_1_3_2_62_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.is.2018.09.001"},{"key":"e_1_3_2_63_2","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591684"},{"key":"e_1_3_2_64_2","doi-asserted-by":"publisher","DOI":"10.1145\/3470482.3479621"},{"key":"e_1_3_2_65_2","article-title":"Policy learning for fairness in ranking","volume":"32","author":"Singh Ashudeep","year":"2019","unstructured":"Ashudeep Singh and Thorsten Joachims. 2019. Policy learning for fairness in ranking. Advances in Neural Information Processing Systems 32 (2019).","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_66_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.is.2014.10.001"},{"key":"e_1_3_2_67_2","doi-asserted-by":"publisher","DOI":"10.7146\/mediekultur.v36i69.121180"},{"key":"e_1_3_2_68_2","doi-asserted-by":"publisher","DOI":"10.1145\/2043932.2043957"},{"key":"e_1_3_2_69_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2021.12.246"},{"key":"e_1_3_2_70_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-020-09768-8"},{"key":"e_1_3_2_71_2","unstructured":"Tim Vieira. 2014. Gumbel-max Trick and Weighted Reservoir Sampling. http:\/\/timvieira.github.io\/blog\/post\/2014\/08\/01\/gumbel-max-trick-and-weighted-reservoir-sampling\/"},{"key":"e_1_3_2_72_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2015.02.016"},{"key":"e_1_3_2_73_2","doi-asserted-by":"publisher","DOI":"10.1093\/jopart\/muy047"},{"key":"e_1_3_2_74_2","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2023.3300547"},{"key":"e_1_3_2_75_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2016.09.040"},{"key":"e_1_3_2_76_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.csda.2007.07.011"},{"key":"e_1_3_2_77_2","doi-asserted-by":"publisher","DOI":"10.1080\/01900692.2018.1498103"},{"key":"e_1_3_2_78_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3382262"},{"key":"e_1_3_2_79_2","article-title":"Exploiting epistemic uncertainty in cold-start recommendation systems","author":"Xiang Yang","year":"2025","unstructured":"Yang Xiang, Li Fan, Chenke Yin, Menglin Kong, and Chengtao Ji. 2025. Exploiting epistemic uncertainty in cold-start recommendation systems. arXiv preprint arXiv:2502.16256 (2025).","journal-title":"arXiv preprint arXiv:2502.16256"},{"key":"e_1_3_2_80_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2022.103100"},{"key":"e_1_3_2_81_2","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645487"},{"key":"e_1_3_2_82_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3338705"},{"key":"e_1_3_2_83_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.physa.2023.128546"},{"key":"e_1_3_2_84_2","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462875"}],"container-title":["ACM Transactions on Recommender Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3729245","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,29]],"date-time":"2025-07-29T12:47:40Z","timestamp":1753793260000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3729245"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,29]]},"references-count":83,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,3,31]]}},"alternative-id":["10.1145\/3729245"],"URL":"https:\/\/doi.org\/10.1145\/3729245","relation":{},"ISSN":["2770-6699"],"issn-type":[{"type":"electronic","value":"2770-6699"}],"subject":[],"published":{"date-parts":[[2025,7,29]]},"assertion":[{"value":"2024-01-17","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-04-02","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-07-29","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}