Re:Item2Vec: Neural Item Embedding for Collaborative Filtering
by meeper16 on Monday July 11, 2016 @06:18AM
(#12070049)
Spotify got this from Berkeley Lab who were doing it in 2005 "Word2Vec is based on an approach from Lawrence Berkeley National Lab" https://www.kaggle.com/c/word2vec-nlp-tutorial/forums/t/1234... which is interesting because the original streaming music site, seeqpod, who powered spotify, was based on vectors for songs, like a song2vec.
Re:Item2Vec: Neural Item Embedding for Collaborative Filtering
by rahimnathwani on Sunday July 10, 2016 @11:42PM
(#12068746)
From the Spotify blog post: "We train a model on subsampled (5%) playlist data using skip-grams and 40 factors."
Any idea what those 40 factors might be?
(The item2vec paper describes using pairs of items that occur in the same set, i.e. just like using n-grams, but without a fixed n, and ignoring ordering.)
Re:Item2Vec: Neural Item Embedding for Collaborative Filtering
by rm999 on Monday July 11, 2016 @12:02AM
(#12068808)
That's the dimensionality of the resulting word vectors in word2vec; in the item2vec paper this is the "dimension parameter m".
Re:Item2Vec: Neural Item Embedding for Collaborative Filtering
by 3pt14159 on Monday July 11, 2016 @09:20AM
(#12070822)
Yeah, I "invented" this in 2011 or 2012 and it was one of the ideas behind the company that I sold. At the time I thought it was a clever hack, but I didn't see it as especially non-obvious.
Re:Item2Vec: Neural Item Embedding for Collaborative Filtering
by neeraj1987 on Thursday July 14, 2016 @05:13AM
(#12092521)
hi,very informative talk; especially with those examples for handling cold start and seeding. any pointers on how the multiple entities are incorporated in the interaction matrix? I understand how user/item attributes may be incorporated in the interaction matrix but multiple entities is something that I am struggling to understand. Pointers to associated literature would help too.
Re:Item2Vec: Neural Item Embedding for Collaborative Filtering
by rm999 on Thursday July 14, 2016 @01:46PM
(#12095874)
This paper covers mixing different types: http://www.csie.ntu.edu.tw/~b97053/paper/Rendle2010FM.pdf (this paper covers a related but different technique). See figure 1 for an example of mixing ratings, indicator variables, and time into a single matrix.
Re:Item2Vec: Neural Item Embedding for Collaborative Filtering
by neeraj1987 on Monday July 18, 2016 @01:45AM
(#12113406)
Thanks a lot :-)
Re:Item2Vec: Neural Item Embedding for Collaborative Filtering
by etangent on Monday July 11, 2016 @07:41AM
(#12070348)
"[before computing SVD], we normalized each entry according to the square root of the product of its row and column sums."
Why didn't they use something that usually works better, like PMI?
Also, I know the paper isn't claiming state-of-the-art, but their SVD results are horrendous. Standard CF would create much better artist-artist pairings with even a medium sized dataset.
As an aside, I've run some quantitative and qualitative tests and have found the best recommendations come from a combination of user-item and item-item. I co-gave a talk at the NYC machine learning meetup recently (https://docs.google.com/presentation/d/1S5Cizi9LFQ7l0bMYtY7g...) that shows how this can work, starting at slide 20. The idea is to create a candidate list of matches using item-item, and then reorder using item-user. I've found this creates "sensible" suggestions using item-item, but truly personalizes when re-ordering. You can remove obvious recommendations by removing popular matches or matches the user has already interacted with (I consider this a business decision rather than something inherent in the algorithm).