5

I am trying to build a recommendation model by using a tensor. In order to recommend an article to a user, I have built a model to predict users' preferable articles.

I am labeling articles based on topics, the result of my learning dataset is a 3-dimensions dataset (USers (X) - Topics (Y) - Time (Z) ), because user's interest might evolve over time, at the same time it doesn't change much.

In order to build predictive models, I usually deal with 2-Dimensions data X,Y and predict based on training/Testing. Now, I am trying to lean how to use the different techniques that might help solving similar problems (like Matrix Factorizations and tensors, Tensor Decompositio, convex tensor completion methods for tensors )

I am little bit lost in literature, what are some good resources (courses/tutorials) to learn more on how to use tensors and related techniques to model similar above-mentioned problems ?

Tim
  • 108,699
  • 20
  • 212
  • 390
user3378649
  • 1,107
  • 4
  • 13
  • 22
  • 1
    Check for examples http://stats.stackexchange.com/questions/198061/why-the-sudden-fascination-with-tensors (unfortunately it's not a full answer for your question) – Tim Jul 04 '16 at 05:30
  • I am voting to close this for being opinion based, but also for being too broad. asking for intuition seems to be the question title, which would be a good question when specified a bit more what one wishes to understand about tensors, but the question diverges in the body text towards basically asking introduction textbooks about algebra, applications in statistics (where it is a bit unclear what sort of textbook more specifically) and basically anything about 2-dimensional data. – Sextus Empiricus Sep 13 '18 at 07:54

0 Answers0