Time+Place: Tuesday 12/04/2016 14:30 Room 337-8 Taub Bld.
Title: Mining causality to predict future events
Speaker: Kira Radinsky - COLLOQUIUM LECTURE http://tx.technion.ac.il/~kirar/
Affiliation: CTO and Co-Founder, SalesPredict and Visiting Professor/Scientist, Technion
Host: Shaul Markovitch

Abstract:


Mark Twain famously said that ''the past does not repeat itself, 
but it rhymes.''

In the spirit of this reflection, I present novel algorithms and methods 
for leveraging large-scale digital histories and human knowledge mined from 
the Web to make real-time predictions about the likelihoods of future human 
and natural events of interest.

I will present a system that mines decades of news reports (1851-2010) 
from the New York Times(NYT), and describe how we can learn to predict 
the future by generalizing sets of concrete transitions in sequences of 
reported news events. In addition to the news corpora, we leverage data from 
freely available Web resources, including Wikipedia, FreeBase, OpenCyc, and 
GeoNames, via the LinkedData platform.

The goal is to build predictive models that generalize from specific 
sets of sequences of events to provide likelihoods of future outcomes, 
based on patterns of evidence observed in near-term Web activities. I 
propose the methods as a means of generating actionable forecasts in advance 
of the occurrence of target events in the world.

I will present one of the first works that demonstrate general, 
unrestricted artificial-intelligence prediction capacity and present methods 
derived from heterogeneous Web sources to make knowledge-intensive reasoning 
about causality and future event prediction, using both automatic feature 
extraction and novel algorithms for generalizing over historical examples.

I will show applications both from the industry as part of my company 
and the activities with the medical organizations I have been leading in 
the last few years.


Short bio:

As the CTO and Co-Founder of SalesPredict, Dr. Kira Radinsky is building 
the next generation predictive marketing solutions that transform the 
way companies acquire and retain customers.
One of the up-and-coming voices in the data science community, she is 
pioneering the field of Web Dynamics and Temporal Information Retrieval. 
Dr. Radinsky gained international recognition for her work at the 
Technion and Microsoft Research, where she developed predictive 
algorithms that recognized the early warning signs of globally impactful 
events, including political riots and disease epidemics. In 2013, she 
was named to the MIT Technology Review's 35 Young Innovators 
Under 35, and in 2015 as Forbes 30 under 30 rising stars in enterprise 
technology. She is a frequent presenter at global tech events, including 
TEDx and the World Wide Web Conference, and she publishes in the Harvard 
Business Review.  Radinsky also serves as visiting professor at the 
Technion, Israel's leading science and technology institute.



Refreshments will be served from 14:15
Lecture starts at 14:30