IEEE Spectrum June, 2015 - 25

RESOURCES_CaREERS

KIRa RaDInsKY
using maChine intelligenCe and
data mining, this entrepreneur
prediCts the future

Kir a r adinsK y is a rising star in prEdiCtivE

analytics. She combines the use of artificial intelligence and online data mining to predict likely futures for individuals, societies,
and businesses. Radinsky made headlines two years ago for developing a series of algorithms that dissect words and phrases
in traditional and social media, Web activity, and search trends
to warn of possible disasters, geopolitical events, and disease
outbreaks. Her system predicted Cuba's first cholera epidemic
in decades and early Arab Spring riots. The algorithm-which
grew out of Radinsky's Ph.D. work at Technion-Israel Institute
of Technology, in Haifa-looks for clues and historical patterns
inferred from online behavior and news articles. "During an
event, people search [for related topics] much more than usual,"
she says. "The system looks for other times we saw a spike in

kira radinsky

that same topic and analyzes what was go- its revenue every quarter-except the first machine learning and artificial intelligence
in 2012, at 26.
ing on in the places that had this same spike." quarter of 2015, when it tripled.
Since graduating, she's served full-time
With the 2012 Cuba cholera outbreak, for
"It's big data meets game theory," Radinsky
example, the system "learned," by perusing says. "There was so much data at each com- as SalesPredict's chief technical officer.
news items, that cholera outbreaks occurred pany about their historical sales, but very few "Getting into predictive analytics usually reafter droughts in Angola in 2006 and large actions were taken to scientifically analyze it." quires master's and Ph.D. degrees in data
storms in Africa in 2007. The algorithm also
As a youth, Radinsky wanted to be a scien- mining and machine learning. Data sciennoted other factors, such as location, water tist. But the summer before high school, she tists have strong math and statistical backcoverage, population density, and economy. botched a research project at a science camp. grounds. It's a very academically oriented
When Cuba presented similar conditions, the "It was biology and computers together. I was field," she says. "For my company, it helps
system warned of an outbreak, and a few in charge of feeding the cells. I was not good if you've worked for a company like Google
weeks later, cholera was reported.
at that, and I killed those cells by mistake. After or have strong engineering skills on how to
Radinsky has parlayed her research into that, they had me process the data instead- scale machine learning systems."
Radinsky believes in developing this technola 3-year-old startup, SalesPredict, with 20 and it turned out to be something I enjoyed."
people on staff and offices near Tel Aviv and in
Radinsky enrolled at Technion in 2002 at ogy to benefit not only business but also sociSan Francisco. SalesPredict focuses on help- just 15, earning extra cash by programming ety. "Mining patterns in data can lead humanity
ing businesses, including several Fortune websites on the side. At 18, she did her man- to a new era of faster scientific discoveries. We
100 companies, find new opportunities for datory Israel Defense Forces duty as a com- are working on several pro bono activities in the
sales or retain existing customers and cli- puter scientist in its intelligence division. She medical domain to apply learning machine alents. The company has raised US $4 million completed bachelor's and master's degrees gorithms to predict cancers and find the driving
from venture funding and has been doubling in computer science in 2009, and a Ph.D. in causes of diseases." -susan karlin
SPECTRUM.IEEE.ORG

nORTh aMERICan

JUn 2015

http://SPECTRUM.IEEE.ORG

Table of Contents for the Digital Edition of IEEE Spectrum June, 2015