Ad targeting in the wild (and data science behind it)

Join us at the next Big Data Novi Sad & Geekstone meetup event.

Coming from Silicon Valley in California, Mihajlo Grbović, PhD will talk about Ad targeting in the wild (and data science behind it).

In recent years online advertising has become increasingly ubiquitous and effective. Advertisements shown to visitors fund sites and apps that publish digital content, manage social networks, and operate e-mail services. Given such large variety of internet resources, determining an appropriate type of advertising for a given platform has become critical to financial success.

In this talk I will give an overview of different approaches we took to adapt ad targeting to a particular platform, including Yahoo Search, Tumblr, and Yahoo Email. Each of these platforms has an unique set of characteristics and signals and that can be leveraged to achieve successful ad targeting. For example, in web search, users communicate a very clear intent through a search query that allows effective ad targeting via bid term keywords defined by advertisers.

However, the search engine can help improve reach and quality of the advertising campaign by finding additional queries that deem relevant to the advertised product. For this purpose, we designed an algorithm that relies on search sessions, ad clicks as well as implicit negative signals, such as short dwell time and skipped ads, to learn latent representations of queries and ads that can be utilized for efficient sponsored search matching. On the other hand, designing an ad targeting platform for a social network such as Tumblr involves mapping the content of blogs and user actions, including likes, reblogs and follows, to an advertising taxonomy.

For this purpose we developed a semi-supervised framework that leverages intensity and recency of categorized user content and actions to create targeting audiences that have been put at advertisers’ disposal. Finally, our work on the next generation of native ad experience in Yahoo Email client focused on serving product recommendation ads based on users’ previously purchased products extracted from email receipts.

In my talk, I will show both offline and online experimental results reported in our research papers. The results show that our approaches significantly outperform existing state-of-the-art, substantially improving a number of key business metrics.

Lecturer

Mihajlo Grbović, PhD

http://photos1.meetupstatic.com/photos/event/d/c/0/2/600_450176322.jpeg

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. My thesis work was on Machine Learning applications in Decentralized Fault Detection. 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. I was a Research Intern at Xerox Research Center Europe, ExxonMobil and Akamai.

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. My work was featured in Wall Street Journal, MIT Technology Review, Scientific American, Market Watch and Popular Science. 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.