Use Collaborative Filtering and Clustering Algorithm in Spark MLIB

[Imre Nagi <im...@gmail.com>]

Hi All,

I'm newbie in spark mlib. In my office I have a statistician who work on
improving our matrix model for our recommendation engine. However he works
on R. He told me that it's quite possible to combine the collaborative
filtering and latent dirichlet allocation (LDA) by doing some computations.

However, in spark mlib, I found that both LDA and Collaborative Filtering
have its own model that we can use later for our needs. My question is how
to combine both model to achieve the same goal as our statistician did?
What kind of operation that I can do to combine these models?

Thanks.
Imre