Coming right from the Recommender Systems conference in San Francisco, I present some latest developments in the field of large scale recommendation engines and machine learning.
6. @torbenbrodt #recsys
Product, ”Data Driven Decisions”
“We take a proposal for an original production or
for a piece of content we’re going to buy and we
plug in all the data we can abou tit into our
models. We’re able to predict reach and hours
for that piece of content even before it exists
with reasonable precision in a way that helps us
to say, ‘this is worth funding’ or ‘that’s not worth
funding,’ ”
NEIL HUNT Netflix
7. @torbenbrodt #recsys
Product, “Search & Recommendation
should (not?) converge”
HECTOR GARCIA-MOLINA
Professor, Stanford University
DEBORA DONATO
StumbleUpon
8. @torbenbrodt #recsys
Product, “Use Human Experts”
ERIC COLSON
Stitch Fix
Humans send you customized
outfits. Machines suggest clothes
and judge stuff.
9. @torbenbrodt #recsys
Product, “Explain your knowledge”
● Xbox explains why their
recommendations are utile
● Cortana builds ML model of user and still
allows to change it
Build Trust!
10. @torbenbrodt #recsys
Product, “Care about Privacy”
once you lose your customer because of
privacy, you will never get him back
solutions
● store user history on client side
● ..
11. @torbenbrodt #recsys
Product, ”Allow User Interaction”
HECTOR GARCIA-MOLINA
Professor, Computer Science and Electrical Engineering
Departments of Stanford University
12. @torbenbrodt #recsys
Product, “active learning”
Why do vague
passive learning when you
can ask the user?
.. implicitly or explicitly
http://en.wikipedia.org/wiki/Active_learning_(machine_learning)
SMRITI BHAGAT
Technicolor
16. @torbenbrodt #recsys
Algorithms, “How does MOE work”
DR. SCOTT CLARK
Yelp
1. Build Gaussian Process (GP) with points
sampled so far
2. Optimize covariance hyperparameters of GP
3. Find point(s) of highest Expected Improvement
within parameter domain
4. Return optimal next best point(s) to sample
https://github.com/Yelp/MOE
17. @torbenbrodt #recsys
Algorithms, “Topic Modelling”
● LDA is standard
● datascience tasks
○ where to cut
○ how many topics
● where to use?
http://en.wikipedia.org/wiki/Topic_model
20. @torbenbrodt #recsys
Metrics, “Dwell Time”
● Client Side
implementation
● Yahoo ensures dwell-time
is comparable across
different context (device,
etc)
● it correlates to clicks, but
is more meaningful
XING YI
Yahoo Labs
25. @torbenbrodt #recsys
Openness, “Connectivity”
● Give students the chance
to learn
● CoLaboratory Notebook
http://venturebeat.com/2014/08/08/google-whips-up-a-
chrome-app-to-let-data-scientists-work-together/
26. @torbenbrodt #recsys
Openness, “Connectivity”
● Azure Marketplace
allows to exchange
machine learning models
● RapidMiner makes
workflows reproducable
https://datamarket.azure.com/browse/data
30. @torbenbrodt #recsys
Crazy Stuff, “Google Deep Learning”
● Application?
○ Pixels, Audio, Searches,
Translation
● Embeddings
● Language Models
● Scalability
JEFF DEAN
Google