addressalign-toparrow-leftarrow-rightbackbellblockcalendarcameraccwcheckchevron-downchevron-leftchevron-rightchevron-small-downchevron-small-leftchevron-small-rightchevron-small-upchevron-upcircle-with-checkcircle-with-crosscircle-with-pluscontroller-playcrossdots-three-verticaleditemptyheartexporteye-with-lineeyefacebookfolderfullheartglobegmailgooglegroupshelp-with-circleimageimagesinstagramFill 1light-bulblinklocation-pinm-swarmSearchmailmessagesminusmoremuplabelShape 3 + Rectangle 1ShapeoutlookpersonJoin Group on CardStartprice-ribbonprintShapeShapeShapeShapeImported LayersImported LayersImported Layersshieldstartickettrashtriangle-downtriangle-uptwitteruserwarningyahoo

Scalable and Flexible Machine Learning With Scala @LinkedIn

Agenda

17:00 - 17:30 Gathering

17:30 - 19:00

Scalable and Flexible Machine Learning With Scala
Machine learning (ML) turns data into predictions about the real world in an almost magical fashion. In this talk we'll show why Scala is a great language for machine learning practitioners and show the audience of Scala programmers how easy it is to start performing machine learning magic themselves.

Presenters:

Vitaly Gordon
Senior Data Scientist at LinkedIn
Vitaly Gordon is a senior data scientist on the LinkedIn Product Data Science team where he develops data products that most of you use every day. Prior to LinkedIn, Vitaly founded the data science team at LivePerson and worked in the 8200 unit, leading a team of researchers in developing algorithms to fight terrorism. His contributions have been recognized through a number of awards including the “Life Source” award, an award given each year deemed most high-impact in saving lives. Vitaly holds a B.Sc in Computer Science and an MBA from the Israeli Institute of Technology.

David Shimon
Data Scientist at LivePerson
David Shimon is a data scientist on Liveperson, where he develops data products that help businesses to create meaningful, real time customer connections. Prior to Liveperson, David developed a machine learning based system on Amadesa, which was acquired by Liveperson. David is a graduate of the Talpiot program, and holds a B.Sc in Computer Science, Mathematics & Physics and MA in Political Science. In his free time, he contributes to the open source projects Open-Knesset and Scalding.

 


Join or login to comment.

  • A former member
    A former member

    An enjoyable and thought-provoking talk. Being a Scala developer already I particularly enjoyed the 2nd half with the various practical examples and code samples.

    March 19, 2013

  • A former member
    A former member

    Hi All,
    Here are the links I've talked about during our talk.
    The lecture about LinkedIn product development - http://bit.ly/114ImKS
    The lecture about Skills and Endorsements - http://slidesha.re/108DGqz
    The slides from this meeting (given in SF) - http://slidesha.re/15LwZdo

    Thanks for coming,
    Vitaly

    March 19, 2013

    • A former member
      A former member

      Pretty clever

      March 19, 2013

    • A former member
      A former member

      Hi Nimrod, The page rank example was more to show about how a simple technique can produce interesting results. Obviously a real implementation will be smarter. About the technique you proposed, it still has the problem of defining those false skills. We actually use endorsements to discover and suggest skills for people. One example is a member of my team that was endorsed for Karaoke even though he didn't have this skill on his page, and he is quite good at it. I don't think any classifier one can build will classify karaoke as spam for a ML Ph.D. Having said that, we do use a very similar technique for the vetting process of our crowd sourced labelers. We use a set of results for both we know the true results (gold) and some that we know false results (coal).

      March 19, 2013

  • Matan S.

    Thanks again for the talk :)
    Practical question - what development environment (and Scala version) do you use for Scala and why?! I use latest version Eclipse and the Scala IDEA plugin, which works but a bit quirky.

    March 18, 2013

    • A former member
      A former member

      We use IntelliJ IDEA 12 (commercial). For Java development it can't be beat; for Scala it's still a little quirky but is getting better all the time -- when we started a couple years back both Eclipse and IDEA had such poor Scala support you really had to WANT to develop in Scala :-) Nowadays it still has quirks but is actually fairly stable and usable.

      1 · March 19, 2013

    • A former member
      A former member

      Also, the sbt crowd seems to prefer vim or Sublime Text 2 -- personally I think both options are viable but require a lot of effort to set up in a usable manner.

      March 19, 2013

  • Ofir M.

    Great presentation! wonderful, passionate intro to practical scala for data science.
    One minor point if you deliver it again - I would have added two slides in the middle - "what is Cascading" and "What is Scalding", to explicitly discuss it for a few minutes.

    March 19, 2013

  • Erez L.

    Vitaly & David - thanks for a great inspiring yet hand on talk!
    You made me install ScalaIDE on my eclipse first thing this morning... cant wait to try it out!

    March 19, 2013

  • Sharon K.

    Great talk, very interesting and fun machine learning examples and scala advocation

    March 19, 2013

  • Yaniv D.

    Great lecture.

    March 19, 2013

  • Nati S.

    Very good presentation indeed.
    Learned new facts about Scala, LivePerson & LinkedIn
    :-)

    March 18, 2013

  • Oded M.

    Missed it, can you send the presentation please?

    March 18, 2013

  • Sagie D.

    Thanks for the talk. Great to see Scala growing

    March 18, 2013

  • Eyal G.

    maybe

    March 18, 2013

  • A former member
    A former member

    @Naama, it is not relevant only for Scala programmers, in fact the talk does not assume any Scala knowledge and provides an intro to Scala. There will be real life machine learning examples both from LinkedIn and LivePerson.

    March 17, 2013

  • Haim B.

    Sounds promising - looking forward to learn from the big guys.

    March 14, 2013

  • Iris R.

    Looking forward

    March 14, 2013

  • Zahy B.

    Sounds interesting

    March 13, 2013

  • Ido H.

    cool! scala! ML!
    pinaktem

    1 · March 13, 2013

  • tamir aldema t.

    very interesting

    March 13, 2013

Our Sponsors

People in this
Meetup are also in:

Sign up

Meetup members, Log in

By clicking "Sign up" or "Sign up using Facebook", you confirm that you accept our Terms of Service & Privacy Policy