• Geekstone
    Meetup
    03/06/16 06:02 PM

    Ad Targeting in the wild

    Mihajlo Grbović
    Amfiteatar centralne zgrade Univerziteta Novi Sad
    besplatan ulaz
Ognjen Stanić
Zoran Tovarloza
Dejan Mijic
Veljko Stanisic
Aleksandar Svorcan
Andrea Jerinic
Vladimir D.
Stanislav Mudrinski
Aleksandar Miljanovic
Marko Anić

Tema

 

U poslednjih nekoliko godina online oglašavanje postaje sve prisutnije i efikasnije. Oglasi se prikazuju posetiocima sajtova i aplikacija, na društvenim mrežama kao i putem emailova. Sa obzirom na tako veliki izbor internet resursa, određivanje odgovarajuće vrste oglašavanja za određenu platformu je postao kritičan faktor za finansijski uspeh.

 

U ovo predavanju Mihajlo će dati pregled različitih pristupa koje su koristili kako bi prilagodili ciljanje oglasa za određenu platformu, uključujući Yahoo Search, Tumblr, i Yahoo Email. Svaka od ovih platformi ima jedinstven set karakteristika i signala koje morate uzeti u obzir kod uspešnog plasiranja oglasa.


U ovom predavanju MIhajlo će prikazati online i offline eksperimentalne rezultate do kojih su došli tokom istraživačkih radova u kompaniji Yahoo. Rezultati pokazuju da su njihovi pristupi značajno nadmašili postojeća naučna istraživanja, konstantnim poboljšanjem niza ključnih poslovnih pokazatelja.

predavač

Geekstone

predavač

Mihajlo Grbović

I joined Yahoo Labs as a Research Scientist in September 2012. Since then, I have been working in the Targeting Sciences group on projects such as Large-scale Behavioral Targeting, Lookalike Modeling, Tumblr Monetization, Email Categorization/Monetization and most recently on Query to Ad matching in Sponsored Search. Some of my biggest accomplishments include building a large scale Interest and Gender Targeting pipeline for Tumblr, training email classifiers used in Yahoo Mail Smart Views that millions of people interact with every day, and introducing the next generation query-ad matching algorithm to Yahoo Sponsored Search. I received my PhD from the Department of Computer Science at Temple University in Philadelphia. During my PhD studies I worked in the areas of Sparse Principal Component Analysis, Anomaly Detection, Preference Learning and Ranking and Memory Constrained Data Mining. My current research interests lie in Ad Targeting, Monetization and Web Search. I published more than 40 papers at top Machine Learning and Data Mining Conferences and Journals, and hold 7 granted and pending patents. Currently, I hold the title of Senior Research Scientist and am leading a team of Research Scientists working on Yahoo's Sponsored Search matching techniques.

KONTAKT
  • Novosadskog sajma 2, 9. sprat
    21000 Novi Sad
    Serbia

  • +381(69)701 456

LOGIN
O NAMA

Geekstone je neprofitna organizacija posvećena okupljanju programera u cilju lakše razmene znanja, iskustava i ideja o programiranju. Osim toga Geekstone je i mesto za "networking" i druženje.

Više
NEWSLETTER
© Geekstone 2015. Sva prava zadržana.
Geekstone © Geekstone 2015. Sva prava zadržana.