Talk:Matrix factorization (recommender systems)

Page contents not supported in other languages.
From Wikipedia, the free encyclopedia

This article only contains a few of basic algorithms. The section for hybrid MF and MF with side information should be expanded --MaurizioFD (talk) 14:19, 14 June 2018 (UTC)[reply]

Using SVD for recommender systems predates 2006, and a first mention is 2000.

* Here is a source from Grouplens from August 2000. "Application of dimensionality reduction in recommender system-a case study" https://apps.dtic.mil/docs/citations/ADA439541.  It can also be found on the grouplens site http://files.grouplens.org/papers/webKDD00.pdf.
* Here is a patent that describes using SVD for recommendation systems, from June 23, 2000, originating from Net Perceptions company.Net Perceptions.  Here is an article about Net Perceptions patent portfolio being sold to Thalveg Data Flow LLC, the new assignee.  https://www.forbes.com/forbes/2005/1114/166.html#166c3f42228e

As an aside, I was there when this happened so want to help to add this historical info. — Preceding unsigned comment added by Fz7 (talkcontribs) 13:42, 5 January 2019 (UTC)[reply]