Metraipolis › archive › dc_10e96ca06be3
You Know What You Will Like: People Predict Their Own Ratings Better Than Recommender Systems — arXiv:2611.06696
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.06696
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-05T18:20:32.413Z
- SHA-256 of the archived text
ee9d3a4224ae10889857aa5d3089fd4b7383fcff849c132bfbed527a624761ee- Stable URL of this page
https://metraipolis.com/documento/dc_10e96ca06be3
How to cite
You Know What You Will Like: People Predict Their Own Ratings Better Than Recommender Systems — arXiv:2611.06696 — arXiv (en), https://arxiv.org/abs/2611.06696 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_10e96ca06be3 (Metraipolis archive dc_10e96ca06be3, sha256 ee9d3a4224ae10889857aa5d3089fd4b7383fcff849c132bfbed527a624761ee)
BibTeX
@misc{dc10e96ca06be3,
title = {You Know What You Will Like: People Predict Their Own Ratings Better Than Recommender Systems — arXiv:2611.06696},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.06696},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_10e96ca06be3; sha256 ee9d3a4224ae10889857aa5d3089fd4b7383fcff849c132bfbed527a624761ee},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.06696. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Recommender systems usually learn what people want from what they have done. Platforms could also ask people directly, but asking is costly: 98.8% of the prompts in our data went unanswered. Theories of statistical prediction imply that a person's own forecast adds little to a recommender algorithm built from many people's behavior. Theories of dispersed knowledge imply that people hold information about their own taste that the data lack. We test the two with the MovieLens Beliefs dataset. In 2023-2024, a homepage prompt asked members how they expected to rate movies they said they had not seen. Of 26,020 such expectations, 551 from 277 members were followed by a rating at least a day later. We compare each expectation with four benchmarks: the platform's own predicted rating, two collaborative-filtering models (matrix factorization and an item neighborhood), and a stack trained on other members' outcomes. The trained models use each member's latest ratings. People predict their own ratings more accurately than all four benchmarks (correlation 0.69, against 0.34 for MovieLens and 0.54 to 0.59 for the trained recommenders). Added to all the machine forecasts and features, the expectation lowers out-of-sample mean squared error by 26%. The gain holds when models are trained on earlier expectations and tested on later ones. A member's earlier expectations about other movies do not replace the current one. In ordering a member's own movies, the trained recommenders are statistically indistinguishable from the person. On old, heavily rated movies, the machines do as well or better. The results reconcile the two theories: the crowd's data suffice where they are rich, and the person adds information about the specific item. We derive four design principles for preference elicitation and recommender evaluation. Tema degli esploratori: economia dei servizi IA (elenco arXiv econ.GN, nuovi lavori del giorno). Categorie arXiv: Human-Computer Interaction (cs.HC) ; General Economics (econ.GN). Pagina del lavoro: https://arxiv.org/abs/2611.06696 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-05T18:14:33.962Z dalla pagina https://arxiv.org/list/econ.GN/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).