How Does a Recommendation Algorithm Decide What You See?
In short: Published research describes recommendation as a forecast built from signals, a candidate stage and a ranking stage, measured against engagement and business goals, while the feedback loops it creates remain largely unexplored.
A 1:25 short film in the series “From Fingers to Qubits”, narrated by intellect_voice_01.
Sources used in this film: Academia.edu (hosted copy of a paper with ACM DOI 10.1145/2959100.2959190), “Deep Neural Networks for YouTube Recommendations”; arXiv (preprint by Aryan Jadon and co-authors), “A Comprehensive Survey of Evaluation Techniques for Recommendation Systems”; IEEE (IEEE Xplore; article published in IEEE's Computer magazine), “Matrix Factorization Techniques for Recommender Systems”; IEEE (IEEE Xplore abstract page), “Amazon.com recommendations: item-to-item collaborative filtering”; arXiv (Cornell University); paper by Ray Jiang et al., Proceedings of AIES '19 (AAAI/ACM), “Degenerate Feedback Loops in Recommender Systems”; Springer Nature (Neural Computing and Applications), “Revisiting recommender systems: an investigative survey - Neural Computing and Applications”.
Sources used in this film
- Academia.edu (hosted copy of a paper with ACM DOI 10.1145/2959100.2959190) — Deep Neural Networks for YouTube Recommendations · View →
- arXiv (preprint by Aryan Jadon and co-authors) — A Comprehensive Survey of Evaluation Techniques for Recommendation Systems · View →
- IEEE (IEEE Xplore; article published in IEEE's Computer magazine) — Matrix Factorization Techniques for Recommender Systems · View →
- IEEE (IEEE Xplore abstract page) — Amazon.com recommendations: item-to-item collaborative filtering · View →
- arXiv (Cornell University); paper by Ray Jiang et al., Proceedings of AIES '19 (AAAI/ACM) — Degenerate Feedback Loops in Recommender Systems · View →
- Springer Nature (Neural Computing and Applications) — Revisiting recommender systems: an investigative survey - Neural Computing and Applications · View →
Opens the Intellect+ feed with this card first. Swipe up for the next one.
Sources
- Summary by Intellect · source: Academia.edu (hosted copy of a paper with ACM DOI 10.1145/2959100.2959190): Deep Neural Networks for YouTube Recommendations
- Also: arXiv (preprint by Aryan Jadon and co-authors): A Comprehensive Survey of Evaluation Techniques for Recommendation Systems
- Also: IEEE (IEEE Xplore; article published in IEEE's Computer magazine): Matrix Factorization Techniques for Recommender Systems
- Also: IEEE (IEEE Xplore abstract page): Amazon.com recommendations: item-to-item collaborative filtering
- Also: arXiv (Cornell University); paper by Ray Jiang et al., Proceedings of AIES '19 (AAAI/ACM): Degenerate Feedback Loops in Recommender Systems
- Also: Springer Nature (Neural Computing and Applications): Revisiting recommender systems: an investigative survey - Neural Computing and Applications
To cite this card, link to https://intellectplus.co.uk/app/how-does-a-recommendation-algorithm-decide-what-you-see.
How we source, check and correct cards: Editorial standards.
General information, not professional advice. Spotted an error? Flag the card or see corrections and complaints.
Intellect Plus is a visual educational discovery platform for exploring fascinating facts and ideas. Brain Food, Not Brain Rot. What is Intellect Plus?
Related
More in Science · Latest · A–Z · All topics
