I’ve been thinking about how one would implement an application that only shows
recommendations. This is partly because people want to build such things.
There are many problems with this including cold start and overfit. However
these problems also face MABs and are solved with sampling
Mahout has changed a lot in the past couple years, becoming more focused on
serving the needs of data workers and scientists who need to experiment
with large matrix math problems. To that end we've broadened the execution
engines that perform the distribution of computation to include Spark and
That is, if you're running the command `mahout`, if you then then run
`which mahout` do you get the version in bin/mahout, or your (I'm assuming)
pre-installed version?
See https://mahout.apache.org/users/sparkbindings/faq.html and
I'm wondering how this is still working for you since this was removed in
0.11.1 per https://issues.apache.org/jira/browse/MAHOUT-1782 but someone
else may know more.
You did rebuild the code and are running that fresh version of `mahout` in
`bin`, right?
On Fri, Sep 16, 2016 at 10:52 PM, Reth