Hi, OP here. I started working on recommender systems in 2016 during my
undergrad, specifically doing music recommendation. I spent about five months
in 2019 trying to make a music startup based on that. However, during that time
I realized that there would probably be more value in having a really good
general-purpose recommender system. i.e. if you're looking for something
specific, use Google, and if you're not looking for something specific, use
Findka. That's the vision anyway.
Some good articles on this topic:
"Search, discovery and marketing"[1]
> Google is very good at giving you what you're looking for, but no good at all
at telling you what you want to find, let alone things you didn't know you
wanted.
"The Big Promise of Recommender Systems"[2] (2011)
> When we evaluate the current generation of recommender systems from the point
of view of the “recommendee,” we find that most recommender systems serve the
goals of the business instead of their users’ interests. Thus we believe that
the big promise of recommender systems has yet to be fulfilled. We foresee a
third wave of recommender systems that act directly on behalf of their users
across a range of domains instead of acting as a sales assistant.
The algorithm currently is dead simple. Just collaborative filtering without
explicitly taking into account content type. So it's naively cross-domain.
Since the data set is still small, there's no need for matrix factorization. I
recompute the whole matrix every hour and store it in memory. See [3] for the
implementation (it only took 30 LOC). That's a little out-of-date but the
general approach hasn't changed.
For the tech stack, I'm using a Clojure web framework + deployment solution
that I made.[4] It's like a self-hosted version of Firebase (I'm running it on
DigitalOcean). See [5].
Some good articles on this topic:
"Search, discovery and marketing"[1]
> Google is very good at giving you what you're looking for, but no good at all at telling you what you want to find, let alone things you didn't know you wanted.
"The Big Promise of Recommender Systems"[2] (2011)
> When we evaluate the current generation of recommender systems from the point of view of the “recommendee,” we find that most recommender systems serve the goals of the business instead of their users’ interests. Thus we believe that the big promise of recommender systems has yet to be fulfilled. We foresee a third wave of recommender systems that act directly on behalf of their users across a range of domains instead of acting as a sales assistant.
The algorithm currently is dead simple. Just collaborative filtering without explicitly taking into account content type. So it's naively cross-domain. Since the data set is still small, there's no need for matrix factorization. I recompute the whole matrix every hour and store it in memory. See [3] for the implementation (it only took 30 LOC). That's a little out-of-date but the general approach hasn't changed.
For the tech stack, I'm using a Clojure web framework + deployment solution that I made.[4] It's like a self-hosted version of Firebase (I'm running it on DigitalOcean). See [5].
[1] https://www.ben-evans.com/benedictevans/2015/6/24/search-dis...
[2] https://www.aaai.org/ojs/index.php/aimagazine/article/view/2...
[3] https://findka.com/blog/rec-sys-in-30-lines/
[4] https://github.com/jacobobryant/biff
[5] https://findka.com/blog/migrating-to-biff/