3. We need to reduce
churn. Okay. I'll look into it.
Lots of conversations like this
4. I figured out that....some
complex stuff about
vector space that'll
improve...
....and that's how we'll
reduce churn.
Sounds good. Let's
do that...
The "a ha" moment isn't the end.
5. Now what?
Any of you know
what Gradient
Boosting is?
So when can we go
live with the new
model?
6.
7. What goes on in the Kludge?
Rewriting Code
Batch Jobs
PMML
13. great for analysis
● Built for analysis and statistics
● Everything is tabular
● Active community; 4000+ packages
14. great for analysis
● Built for analysis and statistics
● Everything is tabular
● Active community; 4000+ packages
bad for applications
● Not web friendly
● Everything is tabular
● Slow
● A list of R grievances:
○ https://github.com/tdsmith/aRrg
18. R code > Compile to Bytecode > Execute from Python
{
“data”: {
“foo”: 100,
“bar”: 200
}
}
Incoming data for
prediction Make prediction
from Python using
compiled R
19. R code > Compile to Bytecode > Execute from Python
Returned via
REST API
Prediction sent back
to Python
webserver{
“prob”: 0.95
}