Treceți la conținutul principal

Profetii despre trecut

Israeli 'web prophet' maps the past to predict the future

Dr. Kira Radinsky, 26, who started studying at the Technion at 15, wins recognition from MIT for pioneering software that finds historical patterns to point the way ahead

 August 24, 2013, 9:01 am 
Dr. Kira Radinsky (Photo credit: Courtesy)
Dr. Kira Radinsky (Photo credit: Courtesy)
Prophecy may still be restricted to those qualified to appear in the Bible, but modern technology has given us the next best thing – the ability to make a very accurate educated guess about what may happen in the future. Work in that area is being led by Dr. Kira Radinsky, an Israeli web technology researcher, and for her accomplishments, Radinsky has been added to a prestigious list of top technology figures under 35 years of age, recently published by an official publication of MIT.
Get The Times of Israel's Daily Edition by email 
and never miss our top stories
And at 26, Radinsky, who was educated at the Technion and did her research work at Microsoft, is one of the younger people on the list – meaning that she is likely to achieve a lot more before she's done.
The "35 Under 35" list has been published by the MIT Technology Review Magazine since 1999, and it showcases the people expected to have an important impact on the future based on their work. A panel of judges reviews researchers' work – hundreds apply for the list each year – and determines which researchers are doing work that will most significantly affect the world in the coming decades. Among previous winners have been Facebook founder Mark Zuckerberg, Google co-founders Sergey Brin and Larry Page, and chief Apple designer Jonathan Ive.
Radinsky, along with her partner Eric Horvitz, co-director at Microsoft Research in Redmond, Washington, developed software that parses the web, seeking patterns — in news and historical archive sites for hints on patterns that have led to outbreaks of disease, deaths, and riots in the past – and comparing those patterns to current conditions. It's a very sophisticated form of data mining, enabling deep analysis of disparate events and seeing how they repeat themselves time after time.
A paper published by Radinksy and Horvitz provides a good example: In 2012, Cuba suffered a major outbreak of cholera, its first in 130 years. Authorities there were totally unprepared to deal with the situation; according to news reports, doctors had declared states of emergency in numerous areas (although there was little official comment from the Cuban government).
But the software designed by Radinsky and Horovitz, their paper said, specifically pointed to the likelihood of a major cholera outbreak in the country. 2011 was a dry year for Cuba, but by mid-2012, rain returned to the country, with the above-average rainy season culminating with Hurricane Sandy in October of that year. The summer rains, and especially Sandy, caused major flooding in some parts of the country, and as the flooding increased, the cholera infection rates rose, the paper said.
While the events – drought, flooding, and cholera – seemed random, the software determined that it should have been expected. Searching 150 years of news reports and historical archives, the software determined a specific correlation between a drought state followed by major flooding, and a subsequent cholera outbreak, especially prominent in poor countries, where flood control was often substandard or non-existent. Weather researchers had long suspected a correlation between flooding and cholera, but it took the "prophecy software" designed by Radinsky and Horovitz to figure it out.
In another cholera example, the system would have predicted a major outbreak of cholera in Bangladesh in 1991, giving medical officials several days to prepare for it, the paper said. Not that the system is foolproof, the paper noted – but it has shown an accuracy rate of between 70% and 80%. That would be better than the 50/50 rate most of us can boast, and could help determine trends and events in many spheres. In fact, Radinksy has started her own business, calledSalesPredict, which combines big data and predictive analytics to help businesses better qualify their leads.
Radinsky began studying at the Technion at age 15, and completed three degrees at the Faculty of Computer Science under the supervision of Prof. Shaul Markovitch. "Kira is a brilliant researcher gifted with unique skills which support her inclusion on this list," said Markovitch. "Kira possesses intense intellect, creativity and curiosity – a rare combination typical of outstanding inventors. In her doctoral study, she tackled a problem that seemed to be unsolvable with the tools currently available – the development of algorithms capable of accurately predicting global events through the use of vast reservoirs of web-based information sources. Her boldness for taking on such a problem and scientific competence that demonstrated her successful solution is what brought her to be included on this list."
Commenting on her selection, Jason Pontin, editor-in-chief and publisher of Technology Review, said "Over the years, we have had success in choosing women and men whose innovations and companies have been profoundly influential on the direction of human affairs. We're proud of our selections and the variety of achievements they celebrate, and we're proud to add Kira to this prestigious list."
For her part, Radinsky said, "It is an honor to be added to this MIT list. I hope this will encourage researchers and scholars from Israel to engage in research in order to build Israel into an empirical research superpower."