Deriving Context from Big Data for Mobile Advertising


Details
*Note, expedite check in at Galvanize; register here (https://www.eventbrite.com/e/sf-data-science-deriving-context-from-big-data-for-mobile-advertising-tickets-21460865025).
About This Talk:
In this meetup, Delroy Cameron will discuss challenges and experiences in gleaning context from big data for mobile advertising.
Unambiguously linking textual phrases in documents to unique concepts in structured background knowledge (i.e., entity disambiguation) is a consequential problem for mobile commerce. Entity disambiguation could impact monetization by facilitating delivery of more contextually relevant ads on mobile. For instance, given the assertion that "Drake will perform in LA this weekend," it would be worthwhile to detect that the word "Drake" refers to rapper Aubrey Drake Graham, and the term "LA" refers to the city of Los Angeles, CA. Dynamically resolving such references could enable advertisers to serve users AppViews to "Buy Tickets in StubHub" for the upcoming event. Delroy Cameron will discuss how the URX team approaches this task, using big data and data science.
Prerequisites:
Intermediate Level
Topics:
Vector Space Model, Machine Learning, Python, Gensim, Information Extraction
What to bring:
Laptop, Mobile Phone
Meet the Speaker:
Delroy Cameron (http://twitter.com/delroycam)is a Data Scientist at URX, where he conducts applied research in the areas of knowledge representation, information extraction, and machine learning. Prior to joining URX, he received his PhD in Computer Science from Wright State University in 2014.


Deriving Context from Big Data for Mobile Advertising